Search

This dissertation consists of three essays examining the effects of overconfidence on decision making. In the first study, I explore the role of board network centrality in mitigating the effects of CEO overconfidence on acquisition decisions. From the perspective of information processing, I argue that more centrally connected boards can guide overconfident CEOs’ attention toward more valuable information, thereby constraining their over-optimism in decision-making. Moreover, I propose that female board representation improves information processing and in turn, strengthens the effect of board networks. I test and confirm my arguments in the context of corporate acquisition. My analysis of 2160 firms from 2002 to 2018 in the context of corporate acquisition supports the proposed two-way and three-way interactions. In the additional analysis, I explored an exogenous variable to proxy for the change of board network centrality and demonstrated the validity of my main results. In the second study, I explore how overconfidence influence CEO decision-making during acquisition waves. Overconfident CEOs are frequently criticized for making value-destroying corporate acquisitions in which they excessively acquire and overpay. I argue that overconfident CEOs often create value and deliver better performance in the acquisition waves given that the motivation and the requirement for action speed for acquisitions that occur in waves are different from those in other acquisition contexts. Specifically, I hypothesize and find that overconfident CEOs are more likely to capture preemption opportunities by acting earlier in acquisition waves, and such rapid moves enable overconfident CEOs to seize high-quality targets or targets with cospecialized assets with lower costs, leading to better acquisition performance. In addition, I find that in acquisition waves, organizational acquisition experience hampers value-add because it reduces overconfident CEO action speed, and associated r

BACKGROUND: Artificial Intelligence(AI)-based solutions for Gleason grading hold promise for pathologists, while image quality inconsistency, continuous data integration needs, and limited generalizability hinder their adoption and scalability. METHODS: We present a comprehensive digital pathology workflow for AI-assisted Gleason grading. It incorporates A!MagQC (image quality control), A!HistoClouds (cloud-based annotation), Pathologist-AI Interaction (PAI) for continuous model improvement, Trained on Akoya-scanned images only, the model utilizes color augmentation and image appearance migration to address scanner variations. We evaluate it on Whole Slide Images (WSI) from another five scanners and conduct validations with pathologists to assess AI efficacy and PAI. RESULTS: Our model achieves an average F1 score of 0.80 on annotations and 0.71 Quadratic Weighted Kappa on WSIs for Akoya-scanned images. Applying our generalization solution increases the average F1 score for Gleason pattern detection from 0.73 to 0.88 on images from other scanners. The model accelerates Gleason scoring time by 43% while maintaining accuracy. Additionally, PAI improve annotation efficiency by 2.5 times and led to further improvements in model performance. CONCLUSIONS: This pipeline represents a notable advancement in AI-assisted Gleason grading for improved consistency, accuracy, and efficiency. Unlike previous methods limited by scanner specificity, our model achieves outstanding performance across diverse scanners. This improvement paves the way for its seamless integration into clinical workflows.

BACKGROUND: Novel noninvasive predictors of disease severity and prognosis in primary sclerosing cholangitis (PSC) are needed. This study evaluated the ability of extracellular matrix remodeling markers to diagnose fibrosis stage and predict PSC-related fibrosis progression and clinical events. METHODS: Liver histology and serum markers of collagen formation (propeptide of type III collagen [Pro-C3], propeptide of type IV collagen, propeptide of type V collagen), collagen degradation (type III collagen matrix metalloproteinase degradation product and type IV collagen matrix metalloproteinase degradation product), and fibrosis (enhanced liver fibrosis [ELF] score and its components [metalloproteinase-1, type III procollagen, hyaluronic acid]) were assessed in samples from baseline to week 96 in patients with PSC enrolled in a study evaluating simtuzumab (NCT01672853). Diagnostic performance for advanced fibrosis (Ishak stages 3-6) and cirrhosis (Ishak stages 5-6) was evaluated by logistic regression and AUROC. Prognostic performance for PSC-related clinical events and fibrosis progression was assessed by AUROC and Wilcoxon rank-sum test. RESULTS: Among 234 patients, 51% had advanced fibrosis and 11% had cirrhosis at baseline. Baseline Pro-C3 and ELF score and its components provided moderate diagnostic ability for discrimination of advanced fibrosis (AUROC 0.73-0.78) and cirrhosis (AUROC 0.73-0.81). Baseline Pro-C3, ELF score, and type III procollagen provided a moderate prognosis for PSC-related clinical events (AUROC 0.70-0.71). Among patients without cirrhosis at baseline, median changes in Pro-C3 and ELF score to week 96 were higher in those with than without progression to cirrhosis (both p < 0.001). CONCLUSIONS: Pro-C3 correlated with fibrosis stage, and Pro-C3 and ELF score provided discrimination of advanced fibrosis and cirrhosis and predicted PSC-related events and fibrosis progression. The results support the clinical utility of Pro-C3 and ELF score for

Transcription coupled-nucleotide excision repair (TC-NER) removes DNA lesions that block RNA polymerase II (Pol II) transcription. A key step in TC-NER is the recruitment of the TFIIH complex, which initiates DNA unwinding and damage verification; however, the mechanism by which TFIIH is recruited during TC-NER, particularly in yeast, remains unclear. Here, we show that the C-terminal domain (CTD) of elongation factor-1 (Elf1) plays a critical role in TC-NER in yeast by binding TFIIH. Analysis of genome-wide repair of UV-induced cyclobutane pyrimidine dimers (CPDs) using CPD-seq indicates that the Elf1 CTD in yeast is required for efficient TC-NER. We show that the Elf1 CTD binds to the pleckstrin homology (PH) domain of the p62 subunit of TFIIH in vitro, and identify a putative TFIIH-interaction region (TIR) in the Elf1 CTD that is important for PH binding and TC-NER. The Elf1 TIR shows functional, structural, and sequence similarities to a conserved TIR in the mammalian UV sensitivity syndrome A (UVSSA) protein, which recruits TFIIH during TC-NER in mammalian cells. These findings suggest that the Elf1 CTD acts as a functional counterpart to mammalian UVSSA in TC-NER by recruiting TFIIH in response to Pol II stalling at DNA lesions.

Mutations in the Cockayne Syndrome group B (CSB) gene cause cancer in mice, but premature aging and severe neurodevelopmental defects in humans. CSB, a member of the SWI/SNF family of chromatin remodelers, plays diverse roles in regulating gene expression and transcription-coupled nucleotide excision repair (TC-NER); however, these functions do not explain the distinct phenotypic differences observed between CSB-deficient mice and humans. During investigating Cockayne Syndrome-associated genome instability, we uncover an intrinsic mechanism that involves elongating RNA polymerase II (RNAPII) undergoing transient pauses at internal T-runs where CSB is required to propel RNAPII forward. Consequently, CSB deficiency retards RNAPII elongation in these regions, and when coupled with G-rich sequences upstream, exacerbates genome instability by promoting R-loop formation. These R-loop prone motifs are notably abundant in relatively long genes related to neuronal functions in the human genome, but less prevalent in the mouse genome. These findings provide mechanistic insights into differential impacts of CSB deficiency on mice versus humans and suggest that the manifestation of the Cockayne Syndrome phenotype in humans results from the progressive evolution of mammalian genomes.

Zhao-Ting Gong,1 Yu-Yan Xiong,1,2 Yu Ning,1 Rui-Jie Tang,1 Jun-Yan Xu,3 Wen-Yang Jiang,1 Xiao-Song Li,1 Li-Li Zhang,1 Cheng Chen,1 Qi Pan,1 Meng-Jin Hu,1 Jing Xu,1 Yue-Jin Yang1 1State Key Laboratory of Cardiovascular Disease, Department of Cardiology, Fuwai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, 100037, People’s Republic of China; 2Department of Cardiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022, People’s Republic of China; 3Department of Guangdong Provincial Key Laboratory of Coronary Heart Disease Prevention, Guangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangzhou, 510080, People’s Republic of ChinaCorrespondence: Yue-Jin Yang, Email yangyjfw@126.comBackground: Exosomes derived from bone marrow mesenchymal stem cells (MSC-exo) have been considered as a promising cell-free therapeutic strategy for ischemic heart disease. Cardioprotective drug pretreatment could be an effective approach to improve the efficacy of MSC-exo. Nicorandil has long been used in clinical practice for cardioprotection. This study aimed to investigate whether the effects of exosomes derived from nicorandil pretreated MSC (MSCNIC-exo) could be enhanced in facilitating cardiac repair after acute myocardial infarction (AMI).Methods: MSCNIC-exo and MSC-exo were collected and injected into the border zone of infarcted hearts 30 minutes after coronary ligation in rats. Macrophage polarization was detected 3 days post-infarction, cardiac function as well as histological pathology were measured on the 28th day after AMI. Macrophages were separated from the bone marrow of rats for in vitro model. Exosomal miRNA sequencing was conducted to identify differentially expressed miRNAs between MSCNIC-exo and MSC-exo. MiRNA mimics and inhibitors were transfected to MSCs or macrop

[EN] 1. Description of methods used for collection/generation of data: Diffraction (electron, synchrotron X-ray, neutron). Infrared spectroscopy multinuclear MAS NMR gas adsorption electron paramagnetic resonance DFT calculations Catalytic reaction 2. Methods for processing the data: Those needed depending on the type of data (SHELX, Rietveld refinement, fast Fourier Transform...). Please, check the paper.

We have obtained the constraints on the density dependence of the symmetry energy from neutron-skin thickness data by parity-violating electron scatterings and neutron-star observables using a Bayesian approach, based on the standard Skyrme-Hartree-Fock (SHF) model and its extension as well as the relativistic mean-field (RMF) model. While the neutron-skin thickness data (neutron-star observables) mostly constrain the symmetry energy at subsaturation (suprasaturation) densities, they may more or less constrain the behavior of the symmetry energy at suprasaturation (subsaturation) densities, depending on the energy-density functional form. Besides showing the final posterior density dependence of the symmetry energy, we also compare the slope parameters of the symmetry energy at 0.10 fm$^{-3}$ as well as the values of the symmetry energy at twice saturation density from three effective nuclear interactions. The present work serves as a comparison study based on relativistic and nonrelativistic energy-density functionals for constraining the nuclear symmetry energy from low to high densities using a Bayesian approach., Comment: 10 pages, 7 figures

Context. Solar jets play a role in the coronal heating and the supply of solar wind. Aims. This study calculated the energies of 23 small-scale jets emerging from a quiet-Sun region to investigate their contributions for coronal heating. Conclusions. Our observations suggest that although these jets cannot provide sufficient energy for the heating of the whole quiet-Sun coronal region, they are likely to account for a significant portion of the energy demand in the local regions where the jets occur.

The atmosphere of Triton was probed directly by observing a ground-based stellar occultation on 6 October 2022. This rare event yielded 23 positive light curves collected from 13 separate observation stations contributing to our campaign. The significance of this event lies in its potential to directly validate the modest pressure fluctuation on Triton, a phenomenon not definitively verified by previous observations, including only five stellar occultations, and the Voyager 2 radio occultation in 1989. Using an approach consistent with a comparable study, we precisely determined a surface pressure of $14.07_{-0.13}^{+0.21}~\mathrm{\mu bar}$ in 2022. This new pressure rules out any significant monotonic variation in pressure between 2017 and 2022 through direct observations, as it is in alignment with the 2017 value. Additionally, both the pressures in 2017 and 2022 align with the 1989 value. This provides further support for the conclusion drawn from the previous volatile transport model simulation, which is consistent with the observed alignment between the pressures in 1989 and 2017; that is to say, the pressure fluctuation is modest. Moreover, this conclusion suggests the existence of a northern polar cap extended down to at least $45^\circ$N$-60^\circ$N and the presence of nitrogen between $30^\circ$S and $0^\circ$., Comment: Astronomy & Astrophysics, in press. 9 pages, 2 figures, 3 tables

Jin J, Xia H, Su Y, et al. J Multidiscip Healthc. 2023;16:4139-4147. The authors wish to correct Figure 1 on page 4143 and Figure 2 on page 4144 after it came to their attention an error had been made during the process of composing images. The corrected Figure 1 is shown below: Figure 1 Continued. Figure 1 SWE images of postpartum anterior uterine walls.Notes: (A). The SWV of 4.88kPa in the postpartum anterior uterine wall for normal pregnant woman with the placenta not located on the anterior wall during pregnancy. (B). The SWV of 16.60kPa in the postpartum anterior uterine wall for normal pregnant woman with the placenta located on the anterior wall during pregnancy. (C). The SWV of 26.71kPa in the postpartum anterior uterine wall for pregnant woman complicated by diabetes mellitus with the placenta located on the anterior wall during pregnancy. The corrected Figure 2 is shown below: Figure 2 Continued. Figure 2 SWE images of postpartum posterior uterine walls.Notes: (A) The SWV of 13.88kPa in the postpartum posterior uterine wall for normal pregnant woman with the placenta not located on the posterior wall during pregnancy. (B) The SWV of 23.40kPa in the postpartum posterior uterine wall for normal pregnant woman with the placenta located on the posterior wall during pregnancy. (C) The SWV of 35.02kPa in the postpartum posterior uterine wall for pregnant woman complicated by diabetes mellitus with the placenta located on the posterior wall during pregnancy. The authors apologize for any inconvenience caused by these errors and for any confusion that may have arisen as a result. They would like to assure the readers that these corrections do not affect the results or conclusions of the paper.

Recent advancements in Large Language Models (LLMs) have attracted considerable interest among researchers to leverage these models to enhance Recommender Systems (RSs). Existing work predominantly utilizes LLMs to generate knowledge-rich texts or utilizes LLM-derived embeddings as features to improve RSs. Although the extensive world knowledge embedded in LLMs generally benefits RSs, the application can only take limited number of users and items as inputs, without adequately exploiting collaborative filtering information. Considering its crucial role in RSs, one key challenge in enhancing RSs with LLMs lies in providing better collaborative filtering information through LLMs. In this paper, drawing inspiration from the in-context learning and chain of thought reasoning in LLMs, we propose the Large Language Models enhanced Collaborative Filtering (LLM-CF) framework, which distils the world knowledge and reasoning capabilities of LLMs into collaborative filtering. We also explored a concise and efficient instruction-tuning method, which improves the recommendation capabilities of LLMs while preserving their general functionalities (e.g., not decreasing on the LLM benchmark). Comprehensive experiments on three real-world datasets demonstrate that LLM-CF significantly enhances several backbone recommendation models and consistently outperforms competitive baselines, showcasing its effectiveness in distilling the world knowledge and reasoning capabilities of LLM into collaborative filtering., Comment: 11 pages

Traditional imitation learning focuses on modeling the behavioral mechanisms of experts, which requires a large amount of interaction history generated by some fixed expert. However, in many streaming applications, such as streaming recommender systems, online decision-makers typically engage in online learning during the decision-making process, meaning that the interaction history generated by online decision-makers includes their behavioral evolution from novice expert to experienced expert. This poses a new challenge for existing imitation learning approaches that can only utilize data from experienced experts. To address this issue, this paper proposes an inverse batched contextual bandit (IBCB) framework that can efficiently perform estimations of environment reward parameters and learned policy based on the expert's behavioral evolution history. Specifically, IBCB formulates the inverse problem into a simple quadratic programming problem by utilizing the behavioral evolution history of the batched contextual bandit with inaccessible rewards. We demonstrate that IBCB is a unified framework for both deterministic and randomized bandit policies. The experimental results indicate that IBCB outperforms several existing imitation learning algorithms on synthetic and real-world data and significantly reduces running time. Additionally, empirical analyses reveal that IBCB exhibits better out-of-distribution generalization and is highly effective in learning the bandit policy from the interaction history of novice experts.

Satellite attitude cotrol is a crucial part of aerospace technology, and model predictive control(MPC) is one of the most promising controllers in this area, which will be less effective if real-time online optimization can not be achieved. Explicit MPC converts the online calculation into a table lookup process, however the solution is difficult to obtain if the system dimension is high or the constraints are complex. The lattice piecewise affine(PWA) function was used to represent the control law of explicit MPC, although the online calculation complexity is reduced, the offline calculation is still prohibitive for complex problems. In this paper, we use the sample points in the feasible region with their corresponding affine functions to construct the lattice PWA approximation of the optimal MPC controller designed for satellite attitude control. The asymptotic stability of satellite attitude control system under lattice PWA approximation has been proven, and simulations are executed to verify that the proposed method can achieve almost the same performance as linear online MPC with much lower online computational complexity and use less fuel than LQR method.

Redundancy is a persistent challenge in Capsule Networks (CapsNet),leading to high computational costs and parameter counts. Although previous works have introduced pruning after the initial capsule layer, dynamic routing's fully connected nature and non-orthogonal weight matrices reintroduce redundancy in deeper layers. Besides, dynamic routing requires iterating to converge, further increasing computational demands. In this paper, we propose an Orthogonal Capsule Network (OrthCaps) to reduce redundancy, improve routing performance and decrease parameter counts. Firstly, an efficient pruned capsule layer is introduced to discard redundant capsules. Secondly, dynamic routing is replaced with orthogonal sparse attention routing, eliminating the need for iterations and fully connected structures. Lastly, weight matrices during routing are orthogonalized to sustain low capsule similarity, which is the first approach to introduce orthogonality into CapsNet as far as we know. Our experiments on baseline datasets affirm the efficiency and robustness of OrthCaps in classification tasks, in which ablation studies validate the criticality of each component. Remarkably, OrthCaps-Shallow outperforms other Capsule Network benchmarks on four datasets, utilizing only 110k parameters, which is a mere 1.25% of a standard Capsule Network's total. To the best of our knowledge, it achieves the smallest parameter count among existing Capsule Networks. Similarly, OrthCaps-Deep demonstrates competitive performance across four datasets, utilizing only 1.2% of the parameters required by its counterparts., Comment: 8 pages

Many countries are facing energy shortage today and most of the global energy is consumed by HVAC systems in buildings. For the scenarios where the energy system is not sufficiently supplied to HVAC systems, a priority-based allocation scheme based on distributed model predictive control is proposed in this paper, which distributes the energy rationally based on priority order. According to the scenarios, two distributed allocation strategies, i.e., one-to-one priority strategy and multi-to-one priority strategy, are developed in this paper and validated by simulation in a building containing three zones and a building containing 36 rooms, respectively. Both strategies fully exploit the potential of predictive control solutions. The experiment shows that our scheme has good scalability and achieve the performance of centralized strategy while making the calculation tractable.

Traffic signal control is important in intelligent transportation system, of which cooperative control is difficult to realize but yet vital. Many methods model multi-intersection traffic networks as grids and address the problem using multi-agent reinforcement learning (RL). Despite these existing studies, there is an opportunity to further enhance our understanding of the connectivity and globality of the traffic networks by capturing the spatiotemporal traffic information with efficient neural networks in deep RL. In this paper, we propose a novel multi-agent actor-critic framework based on an interpretable influence mechanism with a centralized learning and decentralized execution method. Specifically, we first construct an actor-critic framework, for which the piecewise linear neural network (PWLNN), named biased ReLU (BReLU), is used as the function approximator to obtain a more accurate and theoretically grounded approximation. Finally, our proposed framework is validated on two synthetic traffic networks to coordinate signal control between intersections, achieving lower traffic delays across the entire traffic network compared to state-of-the-art (SOTA) performance.

In this report, we present the latest model of the Gemini family, Gemini 1.5 Pro, a highly compute-efficient multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. Gemini 1.5 Pro achieves near-perfect recall on long-context retrieval tasks across modalities, improves the state-of-the-art in long-document QA, long-video QA and long-context ASR, and matches or surpasses Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5 Pro's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 2.1 (200k) and GPT-4 Turbo (128k). Finally, we highlight surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

The burgeoning integration of Artificial Intelligence (AI) into Environmental, Social, and Governance (ESG) initiatives within the financial sector represents a paradigm shift towards more sus-tainable and equitable financial practices. This paper surveys the industrial landscape to delineate the necessity and impact of AI in bolstering ESG frameworks. With the advent of stringent regulatory requirements and heightened stakeholder awareness, financial institutions (FIs) are increasingly compelled to adopt ESG criteria. AI emerges as a pivotal tool in navigating the complex in-terplay of financial activities and sustainability goals. Our survey categorizes AI applications across three main pillars of ESG, illustrating how AI enhances analytical capabilities, risk assessment, customer engagement, reporting accuracy and more. Further, we delve into the critical con-siderations surrounding the use of data and the development of models, underscoring the importance of data quality, privacy, and model robustness. The paper also addresses the imperative of responsible and sustainable AI, emphasizing the ethical dimensions of AI deployment in ESG-related banking processes. Conclusively, our findings suggest that while AI offers transformative potential for ESG in banking, it also poses significant challenges that necessitate careful consideration. The final part of the paper synthesizes the survey's insights, proposing a forward-looking stance on the adoption of AI in ESG practices. We conclude with recommendations with a reference architecture for future research and development, advocating for a balanced approach that leverages AI's strengths while mitigating its risks within the ESG domain., Comment: 31 pages, 14 tables, 3 figures

Recent advancements in large language models have shown impressive performance in general chat. However, their domain-specific capabilities, particularly in information extraction, have certain limitations. Extracting structured information from natural language that deviates from known schemas or instructions has proven challenging for previous prompt-based methods. This motivated us to explore domain-specific modeling in chat-based language models as a solution for extracting structured information from natural language. In this paper, we present ChatUIE, an innovative unified information extraction framework built upon ChatGLM. Simultaneously, reinforcement learning is employed to improve and align various tasks that involve confusing and limited samples. Furthermore, we integrate generation constraints to address the issue of generating elements that are not present in the input. Our experimental results demonstrate that ChatUIE can significantly improve the performance of information extraction with a slight decrease in chatting ability., Comment: Accepted by LREC-COLING 2024

In this paper, we address the issue of using logic rules to explain the results from legal case retrieval. The task is critical to legal case retrieval because the users (e.g., lawyers or judges) are highly specialized and require the system to provide logical, faithful, and interpretable explanations before making legal decisions. Recently, research efforts have been made to learn explainable legal case retrieval models. However, these methods usually select rationales (key sentences) from the legal cases as explanations, failing to provide faithful and logically correct explanations. In this paper, we propose Neural-Symbolic enhanced Legal Case Retrieval (NS-LCR), a framework that explicitly conducts reasoning on the matching of legal cases through learning case-level and law-level logic rules. The learned rules are then integrated into the retrieval process in a neuro-symbolic manner. Benefiting from the logic and interpretable nature of the logic rules, NS-LCR is equipped with built-in faithful explainability. We also show that NS-LCR is a model-agnostic framework that can be plugged in for multiple legal retrieval models. To showcase NS-LCR's superiority, we enhance existing benchmarks by adding manually annotated logic rules and introducing a novel explainability metric using Large Language Models (LLMs). Our comprehensive experiments reveal NS-LCR's effectiveness for ranking, alongside its proficiency in delivering reliable explanations for legal case retrieval., Comment: accepted by lrec-coling 2024

Camouflaged object detection (COD) and salient object detection (SOD) are two distinct yet closely-related computer vision tasks widely studied during the past decades. Though sharing the same purpose of segmenting an image into binary foreground and background regions, their distinction lies in the fact that COD focuses on concealed objects hidden in the image, while SOD concentrates on the most prominent objects in the image. Previous works achieved good performance by stacking various hand-designed modules and multi-scale features. However, these carefully-designed complex networks often performed well on one task but not on another. In this work, we propose a simple yet effective network (SENet) based on vision Transformer (ViT), by employing a simple design of an asymmetric ViT-based encoder-decoder structure, we yield competitive results on both tasks, exhibiting greater versatility than meticulously crafted ones. Furthermore, to enhance the Transformer's ability to model local information, which is important for pixel-level binary segmentation tasks, we propose a local information capture module (LICM). We also propose a dynamic weighted loss (DW loss) based on Binary Cross-Entropy (BCE) and Intersection over Union (IoU) loss, which guides the network to pay more attention to those smaller and more difficult-to-find target objects according to their size. Moreover, we explore the issue of joint training of SOD and COD, and propose a preliminary solution to the conflict in joint training, further improving the performance of SOD. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness of our method. The code is available at https://github.com/linuxsino/SENet., Comment: submitted to IEEE TIP

Large language models (LLMs) are now increasingly utilized for role-playing tasks, especially in impersonating domain-specific experts, primarily through role-playing prompts. When interacting in real-world scenarios, the decision-making abilities of a role significantly shape its behavioral patterns. In this paper, we concentrate on evaluating the decision-making abilities of LLMs post role-playing thereby validating the efficacy of role-playing. Our goal is to provide metrics and guidance for enhancing the decision-making abilities of LLMs in role-playing tasks. Specifically, we first use LLMs to generate virtual role descriptions corresponding to the 16 personality types of Myers-Briggs Type Indicator (abbreviated as MBTI) representing a segmentation of the population. Then we design specific quantitative operations to evaluate the decision-making abilities of LLMs post role-playing from four aspects: adaptability, exploration$\&$exploitation trade-off ability, reasoning ability, and safety. Finally, we analyze the association between the performance of decision-making and the corresponding MBTI types through GPT-4. Extensive experiments demonstrate stable differences in the four aspects of decision-making abilities across distinct roles, signifying a robust correlation between decision-making abilities and the roles emulated by LLMs. These results underscore that LLMs can effectively impersonate varied roles while embodying their genuine sociological characteristics.

In pursuit of fairness and balanced development, recommender systems (RS) often prioritize group fairness, ensuring that specific groups maintain a minimum level of exposure over a given period. For example, RS platforms aim to ensure adequate exposure for new providers or specific categories of items according to their needs. Modern industry RS usually adopts a two-stage pipeline: stage-1 (retrieval stage) retrieves hundreds of candidates from millions of items distributed across various servers, and stage-2 (ranking stage) focuses on presenting a small-size but accurate selection from items chosen in stage-1. Existing efforts for ensuring amortized group exposures focus on stage-2, however, stage-1 is also critical for the task. Without a high-quality set of candidates, the stage-2 ranker cannot ensure the required exposure of groups. Previous fairness-aware works designed for stage-2 typically require accessing and traversing all items. In stage-1, however, millions of items are distributively stored in servers, making it infeasible to traverse all of them. How to ensure group exposures in the distributed retrieval process is a challenging question. To address this issue, we introduce a model named FairSync, which transforms the problem into a constrained distributed optimization problem. Specifically, FairSync resolves the issue by moving it to the dual space, where a central node aggregates historical fairness data into a vector and distributes it to all servers. To trade off the efficiency and accuracy, the gradient descent technique is used to periodically update the parameter of the dual vector. The experiment results on two public recommender retrieval datasets showcased that FairSync outperformed all the baselines, achieving the desired minimum level of exposures while maintaining a high level of retrieval accuracy., Comment: Accepted in WWW'24

For the linear inverse problem with sparsity constraints, the $l_0$ regularized problem is NP-hard, and existing approaches either utilize greedy algorithms to find almost-optimal solutions or to approximate the $l_0$ regularization with its convex counterparts. In this paper, we propose a novel and concise regularization, namely the sparse group $k$-max regularization, which can not only simultaneously enhance the group-wise and in-group sparsity, but also casts no additional restraints on the magnitude of variables in each group, which is especially important for variables at different scales, so that it approximate the $l_0$ norm more closely. We also establish an iterative soft thresholding algorithm with local optimality conditions and complexity analysis provided. Through numerical experiments on both synthetic and real-world datasets, we verify the effectiveness and flexibility of the proposed method., Comment: 7 pages, accepted to American Control Conference 2024

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval aims to capture the list-level contextual features to return a better list, mainly including reranking and truncation. Reranking finely re-scores the documents in the list. Truncation dynamically determines the cut-off point of the ranked list to achieve the trade-off between overall relevance and avoiding misinformation from irrelevant documents. Previous studies treat them as two separate tasks and model them separately. However, the separation is not optimal. First, it is hard to share the contextual information of the ranking list between the two tasks. Second, the separate pipeline usually meets the error accumulation problem, where the small error from the reranking stage can largely affect the truncation stage. To solve these problems, we propose a Reranking-Truncation joint model (GenRT) that can perform the two tasks concurrently. GenRT integrates reranking and truncation via generative paradigm based on encoder-decoder architecture. We also design the novel loss functions for joint optimization to make the model learn both tasks. Sharing parameters by the joint model is conducive to making full use of the common modeling information of the two tasks. Besides, the two tasks are performed concurrently and co-optimized to solve the error accumulation problem between separate stages. Experiments on public learning-to-rank benchmarks and open-domain Q\&A tasks show that our method achieves SOTA performance on both reranking and truncation tasks for web search and retrieval-augmented LLMs., Comment: Accepted by WWW 2024

Arm Cortex-M processors are the most widely used 32-bit microcontrollers among embedded and Internet-of-Things devices. Despite the widespread usage, there has been little effort in summarizing their hardware security features, characterizing the limitations and vulnerabilities of their hardware and software stack, and systematizing the research on securing these systems. The goals and contributions of this paper are multi-fold. First, we analyze the hardware security limitations and issues of Cortex-M systems. Second, we conducted a deep study of the software stack designed for Cortex-M and revealed its limitations, which is accompanied by an empirical analysis of 1,797 real-world firmware. Third, we categorize the reported bugs in Cortex-M software systems. Finally, we systematize the efforts that aim at securing Cortex-M systems and evaluate them in terms of the protections they offer, runtime performance, required hardware features, etc. Based on the insights, we develop a set of recommendations for the research community and MCU software developers., Comment: To Appear in the 18th USENIX WOOT Conference on Offensive Technologies, August 12-13, 2024

In this work, we present HuixiangDou, a technical assistant powered by Large Language Models (LLM). This system is designed to assist algorithm developers by providing insightful responses to questions related to open-source algorithm projects, such as computer vision and deep learning projects from OpenMMLab. We further explore the integration of this assistant into the group chats of instant messaging (IM) tools such as WeChat and Lark. Through several iterative improvements and trials, we have developed a sophisticated technical chat assistant capable of effectively answering users' technical questions without causing message flooding. This paper's contributions include: 1) Designing an algorithm pipeline specifically for group chat scenarios; 2) Verifying the reliable performance of text2vec in task rejection; 3) Identifying three critical requirements for LLMs in technical-assistant-like products, namely scoring ability, In-Context Learning (ICL), and Long Context. We have made the source code, android app and web service available at Github (https://github.com/internlm/huixiangdou), OpenXLab (https://openxlab.org.cn/apps/detail/tpoisonooo/huixiangdou-web) and YouTube (https://youtu.be/ylXrT-Tei-Y) to aid in future research and application. HuixiangDou is applicable to any group chat within IM tools., Comment: 13 pages, 4 figures

Reinforcement learning (RL) has gained traction for enhancing user long-term experiences in recommender systems by effectively exploring users' interests. However, modern recommender systems exhibit distinct user behavioral patterns among tens of millions of items, which increases the difficulty of exploration. For example, user behaviors with different activity levels require varying intensity of exploration, while previous studies often overlook this aspect and apply a uniform exploration strategy to all users, which ultimately hurts user experiences in the long run. To address these challenges, we propose User-Oriented Exploration Policy (UOEP), a novel approach facilitating fine-grained exploration among user groups. We first construct a distributional critic which allows policy optimization under varying quantile levels of cumulative reward feedbacks from users, representing user groups with varying activity levels. Guided by this critic, we devise a population of distinct actors aimed at effective and fine-grained exploration within its respective user group. To simultaneously enhance diversity and stability during the exploration process, we further introduce a population-level diversity regularization term and a supervision module. Experimental results on public recommendation datasets demonstrate that our approach outperforms all other baselines in terms of long-term performance, validating its user-oriented exploration effectiveness. Meanwhile, further analyses reveal our approach's benefits of improved performance for low-activity users as well as increased fairness among users.

To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion. However, existing approaches face two primary challenges: knowledge mismatch between public available knowledge graphs and the specific domain of the task at hand, and poor information compliance of LLMs with knowledge graphs. In this paper, we leverage a small set of labeled samples and a large-scale corpus to efficiently construct domain-specific knowledge graphs by an LLM, addressing the issue of knowledge mismatch. Additionally, we propose a three-stage KG-LLM alignment strategyto enhance the LLM's capability to utilize information from knowledge graphs. We conduct experiments with a limited-sample setting on two biomedical question-answering datasets, and the results demonstrate that our approach outperforms existing baselines., Comment: ACL2024 Findings

Recently, researchers have uncovered that neural retrieval models prefer AI-generated content (AIGC), called source bias. Compared to active search behavior, recommendation represents another important means of information acquisition, where users are more prone to source bias. Furthermore, delving into the recommendation scenario, as AIGC becomes integrated within the feedback loop involving users, data, and the recommender system, it progressively contaminates the candidate items, the user interaction history, and ultimately, the data used to train the recommendation models. How and to what extent the source bias affects the neural recommendation models within feedback loop remains unknown. In this study, we extend the investigation of source bias into the realm of recommender systems, specifically examining its impact across different phases of the feedback loop. We conceptualize the progression of AIGC integration into the recommendation content ecosystem in three distinct phases-HGC dominate, HGC-AIGC coexist, and AIGC dominance-each representing past, present, and future states, respectively. Through extensive experiments across three datasets from diverse domains, we demonstrate the prevalence of source bias and reveal a potential digital echo chamber with source bias amplification throughout the feedback loop. This trend risks creating a recommender ecosystem with limited information source, such as AIGC, being disproportionately recommended. To counteract this bias and prevent its escalation in the feedback loop, we introduce a black-box debiasing method that maintains model impartiality towards both HGC and AIGC. Our experimental results validate the effectiveness of the proposed debiasing method, confirming its potential to disrupt the feedback loop.

Recently, tool learning with large language models (LLMs) has emerged as a promising paradigm for augmenting the capabilities of LLMs to tackle highly complex problems. Despite growing attention and rapid advancements in this field, the existing literature remains fragmented and lacks systematic organization, posing barriers to entry for newcomers. This gap motivates us to conduct a comprehensive survey of existing works on tool learning with LLMs. In this survey, we focus on reviewing existing literature from the two primary aspects (1) why tool learning is beneficial and (2) how tool learning is implemented, enabling a comprehensive understanding of tool learning with LLMs. We first explore the "why" by reviewing both the benefits of tool integration and the inherent benefits of the tool learning paradigm from six specific aspects. In terms of "how", we systematically review the literature according to a taxonomy of four key stages in the tool learning workflow: task planning, tool selection, tool calling, and response generation. Additionally, we provide a detailed summary of existing benchmarks and evaluation methods, categorizing them according to their relevance to different stages. Finally, we discuss current challenges and outline potential future directions, aiming to inspire both researchers and industrial developers to further explore this emerging and promising area. We also maintain a GitHub repository to continually keep track of the relevant papers and resources in this rising area at \url{https://github.com/quchangle1/LLM-Tool-Survey}.

Recently, the integration of external tools with Large Language Models (LLMs) has emerged as a promising approach to overcome the inherent constraints of their pre-training data. However, realworld applications often involve a diverse range of tools, making it infeasible to incorporate all tools directly into LLMs due to constraints on input length and response time. Therefore, to fully exploit the potential of tool-augmented LLMs, it is crucial to develop an effective tool retrieval system. Existing tool retrieval methods techniques mainly rely on semantic matching between user queries and tool descriptions, which often results in the selection of redundant tools. As a result, these methods fail to provide a complete set of diverse tools necessary for addressing the multifaceted problems encountered by LLMs. In this paper, we propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools. Specifically, we first fine-tune the PLM-based retrieval models to capture the semantic relationships between queries and tools in the semantic learning stage. Subsequently, we construct three bipartite graphs among queries, scenes, and tools and introduce a dual-view graph collaborative learning framework to capture the intricate collaborative relationships among tools during the collaborative learning stage. Extensive experiments on both the open benchmark and the newly introduced ToolLens dataset show that COLT achieves superior performance. Notably, the performance of BERT-mini (11M) with our proposed model framework outperforms BERT-large (340M), which has 30 times more parameters. Additionally, we plan to publicly release the ToolLens dataset to support further research in tool retrieval.

In real-world recommender systems, such as in the music domain, repeat consumption is a common phenomenon where users frequently listen to a small set of preferred songs or artists repeatedly. The key point of modeling repeat consumption is capturing the temporal patterns between a user's repeated consumption of the items. Existing studies often rely on heuristic assumptions, such as assuming an exponential distribution for the temporal gaps. However, due to the high complexity of real-world recommender systems, these pre-defined distributions may fail to capture the intricate dynamic user consumption patterns, leading to sub-optimal performance. Drawing inspiration from the flexibility of neural ordinary differential equations (ODE) in capturing the dynamics of complex systems, we propose ReCODE, a novel model-agnostic framework that utilizes neural ODE to model repeat consumption. ReCODE comprises two essential components: a user's static preference prediction module and the modeling of user dynamic repeat intention. By considering both immediate choices and historical consumption patterns, ReCODE offers comprehensive modeling of user preferences in the target context. Moreover, ReCODE seamlessly integrates with various existing recommendation models, including collaborative-based and sequential-based models, making it easily applicable in different scenarios. Experimental results on two real-world datasets consistently demonstrate that ReCODE significantly improves the performance of base models and outperforms other baseline methods., Comment: Accepted by SIGIR 2024 (Short Paper)

The proliferation of Large Language Models (LLMs) has led to an influx of AI-generated content (AIGC) on the internet, transforming the corpus of Information Retrieval (IR) systems from solely human-written to a coexistence with LLM-generated content. The impact of this surge in AIGC on IR systems remains an open question, with the primary challenge being the lack of a dedicated benchmark for researchers. In this paper, we introduce Cocktail, a comprehensive benchmark tailored for evaluating IR models in this mixed-sourced data landscape of the LLM era. Cocktail consists of 16 diverse datasets with mixed human-written and LLM-generated corpora across various text retrieval tasks and domains. Additionally, to avoid the potential bias from previously included dataset information in LLMs, we also introduce an up-to-date dataset, named NQ-UTD, with queries derived from recent events. Through conducting over 1,000 experiments to assess state-of-the-art retrieval models against the benchmarked datasets in Cocktail, we uncover a clear trade-off between ranking performance and source bias in neural retrieval models, highlighting the necessity for a balanced approach in designing future IR systems. We hope Cocktail can serve as a foundational resource for IR research in the LLM era, with all data and code publicly available at \url{https://github.com/KID-22/Cocktail}., Comment: Accepted by Findings of ACL 2024; Datasets Link: https://huggingface.co/IR-Cocktail

Driven by sustainability and economic considerations, two-sided recommendation platforms are required to satisfy the needs of both users and providers. Previous studies often indicate that the two sides' needs differ in urgency: providers have relatively long-term exposure requirements, while users desire short-term, accurate services. However, our empirical study reveals that existing methods for balancing fairness and accuracy often fail to ensure both long-term fairness and short-term accuracy under fluctuating user traffic in real applications. Notably, when user traffic is low, user experience tends to decline significantly. Then, we conducted a theoretical analysis confirming that user traffic is a crucial factor in such a trade-off problem. Ensuring accuracy and fairness under variable user traffic remains a challenge. Inspired by the bankruptcy problem in economics, we propose a novel fairness-aware re-ranking approach called BankFair. BankFair intuitively uses the Talmud rule to leverage periods of high user traffic to compensate for periods of low traffic, ensuring consistent user service while maintaining long-term fairness. BankFair is composed of two modules: (1) utilizing the Talmud rule to determine the necessary degree of fairness across varying user traffic periods, and (2) implementing an online re-ranking algorithm based on the fairness degree established by the Talmud rule. Experiments on one publicly available and one real industrial dataset demonstrate that BankFair outperforms all baselines in terms of both accuracy and provider fairness.

The rapid advancement of large language models has given rise to a plethora of applications across a myriad of real-world tasks, mainly centered on aligning with human intent. However, the complexities inherent in human intent necessitate a dependence on labor-intensive and time-consuming human evaluation. To alleviate this constraint, we delve into the paradigm of employing open-source large language models as evaluators, aligning with the prevailing trend of utilizing GPT-4. Particularly, we present a step-by-step evaluation framework: \textbf{Fennec}, capable of \textbf{F}ine-grained \textbf{E}valuatio\textbf{N} and correctio\textbf{N} \textbf{E}xtended through bran\textbf{C}hing and bridging. Specifically, the branching operation dissects the evaluation task into various dimensions and granularities, thereby alleviating the challenges associated with evaluation. Concurrently, the bridging operation amalgamates diverse training datasets, augmenting the variety of evaluation tasks. In experimental trials, our 7B model consistently outperforms open-source larger-scale evaluation models across various widely adopted benchmarks in terms of both \textit{Agreement} and \textit{Consistency}, closely approaching the capabilities of GPT-4. We employ the fine-grained correction capabilities induced by the evaluation model to refine multiple model responses, and the results show that the refinement elevates the quality of responses, leading to an improvement of 1-2 points on the MT-Bench. Our code is available at Github\footnote{\url{https://github.com/dropreg/Fennec}}.

In-context learning has been extensively validated in large language models. However, the mechanism and selection strategy for in-context example selection, which is a crucial ingredient in this approach, lacks systematic and in-depth research. In this paper, we propose a data compression approach to the selection of in-context examples. We introduce a two-stage method that can effectively choose relevant examples and retain sufficient information about the training dataset within the in-context examples. Our method shows a significant improvement of an average of 5.90% across five different real-world datasets using four language models., Comment: Accepted by ACL 2024 finding

With the rapid advancement of large language models (LLMs), information retrieval (IR) systems, such as search engines and recommender systems, have undergone a significant paradigm shift. This evolution, while heralding new opportunities, introduces emerging challenges, particularly in terms of biases and unfairness, which may threaten the information ecosystem. In this paper, we present a comprehensive survey of existing works on emerging and pressing bias and unfairness issues in IR systems when the integration of LLMs. We first unify bias and unfairness issues as distribution mismatch problems, providing a groundwork for categorizing various mitigation strategies through distribution alignment. Subsequently, we systematically delve into the specific bias and unfairness issues arising from three critical stages of LLMs integration into IR systems: data collection, model development, and result evaluation. In doing so, we meticulously review and analyze recent literature, focusing on the definitions, characteristics, and corresponding mitigation strategies associated with these issues. Finally, we identify and highlight some open problems and challenges for future work, aiming to inspire researchers and stakeholders in the IR field and beyond to better understand and mitigate bias and unfairness issues of IR in this LLM era. We also consistently maintain a GitHub repository for the relevant papers and resources in this rising direction at https://github.com/KID-22/LLM-IR-Bias-Fairness-Survey.

Nowadays, many platforms provide users with both search and recommendation services as important tools for accessing information. The phenomenon has led to a correlation between user search and recommendation behaviors, providing an opportunity to model user interests in a fine-grained way. Existing approaches either model user search and recommendation behaviors separately or overlook the different transitions between user search and recommendation behaviors. In this paper, we propose a framework named UniSAR that effectively models the different types of fine-grained behavior transitions for providing users a Unified Search And Recommendation service. Specifically, UniSAR models the user transition behaviors between search and recommendation through three steps: extraction, alignment, and fusion, which are respectively implemented by transformers equipped with pre-defined masks, contrastive learning that aligns the extracted fine-grained user transitions, and cross-attentions that fuse different transitions. To provide users with a unified service, the learned representations are fed into the downstream search and recommendation models. Joint learning on both search and recommendation data is employed to utilize the knowledge and enhance each other. Experimental results on two public datasets demonstrated the effectiveness of UniSAR in terms of enhancing both search and recommendation simultaneously. The experimental analysis further validates that UniSAR enhances the results by successfully modeling the user transition behaviors between search and recommendation., Comment: Accepted by SIGIR 2024

Medical image processing usually requires a model trained with carefully crafted datasets due to unique image characteristics and domain-specific challenges, especially in pathology. Primitive detection and segmentation in digitized tissue samples are essential for objective and automated diagnosis and prognosis of cancer. SAM (Segment Anything Model) has recently been developed to segment general objects from natural images with high accuracy, but it requires human prompts to generate masks. In this work, we present a novel approach that adapts pre-trained natural image encoders of SAM for detection-based region proposals. Regions proposed by a pre-trained encoder are sent to cascaded feature propagation layers for projection. Then, local semantic and global context is aggregated from multi-scale for bounding box localization and classification. Finally, the SAM decoder uses the identified bounding boxes as essential prompts to generate a comprehensive primitive segmentation map. The entire base framework, SAM, requires no additional training or fine-tuning but could produce an end-to-end result for two fundamental segmentation tasks in pathology. Our method compares with state-of-the-art models in F1 score for nuclei detection and binary/multiclass panoptic(bPQ/mPQ) and mask quality(dice) for segmentation quality on the PanNuke dataset while offering end-to-end efficiency. Our model also achieves remarkable Average Precision (+4.5%) on the secondary dataset (HuBMAP Kidney) compared to Faster RCNN. The code is publicly available at https://github.com/learner-codec/autoprom_sam., Comment: 2024 IEEE International Symposium on Biomedical Imaging

Implementing obstacle avoidance in dynamic environments is a challenging problem for robots. Model predictive control (MPC) is a popular strategy for dealing with this type of problem, and recent work mainly uses control barrier function (CBF) as hard constraints to ensure that the system state remains in the safe set. However, in crowded scenarios, effective solutions may not be obtained due to infeasibility problems, resulting in degraded controller performance. We propose a new MPC framework that integrates CBF to tackle the issue of obstacle avoidance in dynamic environments, in which the infeasibility problem induced by hard constraints operating over the whole prediction horizon is solved by softening the constraints and introducing exact penalty, prompting the robot to actively seek out new paths. At the same time, generalized CBF is extended as a single-step safety constraint of the controller to enhance the safety of the robot during navigation. The efficacy of the proposed method is first shown through simulation experiments, in which a double-integrator system and a unicycle system are employed, and the proposed method outperforms other controllers in terms of safety, feasibility, and navigation efficiency. Furthermore, real-world experiment on an MR1000 robot is implemented to demonstrate the effectiveness of the proposed method.

Incorporating Search and Recommendation (S&R) services within a singular application is prevalent in online platforms, leading to a new task termed open-app motivation prediction, which aims to predict whether users initiate the application with the specific intent of information searching, or to explore recommended content for entertainment. Studies have shown that predicting users' motivation to open an app can help to improve user engagement and enhance performance in various downstream tasks. However, accurately predicting open-app motivation is not trivial, as it is influenced by user-specific factors, search queries, clicked items, as well as their temporal occurrences. Furthermore, these activities occur sequentially and exhibit intricate temporal dependencies. Inspired by the success of the Neural Hawkes Process (NHP) in modeling temporal dependencies in sequences, this paper proposes a novel neural Hawkes process model to capture the temporal dependencies between historical user browsing and querying actions. The model, referred to as Neural Hawkes Process-based Open-App Motivation prediction model (NHP-OAM), employs a hierarchical transformer and a novel intensity function to encode multiple factors, and open-app motivation prediction layer to integrate time and user-specific information for predicting users' open-app motivations. To demonstrate the superiority of our NHP-OAM model and construct a benchmark for the Open-App Motivation Prediction task, we not only extend the public S&R dataset ZhihuRec but also construct a new real-world Open-App Motivation Dataset (OAMD). Experiments on these two datasets validate NHP-OAM's superiority over baseline models. Further downstream application experiments demonstrate NHP-OAM's effectiveness in predicting users' Open-App Motivation, highlighting the immense application value of NHP-OAM., Comment: Accepted by SIGIR 2024

The traditional Kalman filter (KF) is widely applied in control systems, but it relies heavily on the accuracy of the system model and noise parameters, leading to potential performance degradation when facing inaccuracies. To address this issue, introducing neural networks into the KF framework offers a data-driven solution to compensate for these inaccuracies, improving the filter's performance while maintaining interpretability. Nevertheless, existing studies mostly employ recurrent neural network (RNN), which fails to fully capture the dependencies among state sequences and lead to an unstable training process. In this paper, we propose a novel Kalman filtering algorithm named the attention Kalman filter (AtKF), which incorporates a self-attention network to capture the dependencies among state sequences. To address the instability in the recursive training process, a parallel pre-training strategy is devised. Specifically, this strategy involves piecewise linearizing the system via lattice trajectory piecewise linear (LTPWL) expression, and generating pre-training data through a batch estimation algorithm, which exploits the self-attention mechanism's parallel processing ability. Experimental results on a two-dimensional nonlinear system demonstrate that AtKF outperforms other filters under noise disturbances and model mismatches., Comment: 7 pages, 4 figures

Multi-task learning (MTL) is a paradigm that simultaneously learns multiple tasks by sharing information at different levels, enhancing the performance of each individual task. While previous research has primarily focused on feature-level or parameter-level task relatedness, and proposed various model architectures and learning algorithms to improve learning performance, we aim to explore output-level task relatedness. This approach introduces a posteriori information into the model, considering that different tasks may produce correlated outputs with mutual influences. We achieve this by incorporating a feedback mechanism into MTL models, where the output of one task serves as a hidden feature for another task, thereby transforming a static MTL model into a dynamic one. To ensure the training process converges, we introduce a convergence loss that measures the trend of a task's outputs during each iteration. Additionally, we propose a Gumbel gating mechanism to determine the optimal projection of feedback signals. We validate the effectiveness of our method and evaluate its performance through experiments conducted on several baseline models in spoken language understanding., Comment: submitted to CDC2024

Fair re-ranking aims to redistribute ranking slots among items more equitably to ensure responsibility and ethics. The exploration of redistribution problems has a long history in economics, offering valuable insights for conceptualizing fair re-ranking as a taxation process. Such a formulation provides us with a fresh perspective to re-examine fair re-ranking and inspire the development of new methods. From a taxation perspective, we theoretically demonstrate that most previous fair re-ranking methods can be reformulated as an item-level tax policy. Ideally, a good tax policy should be effective and conveniently controllable to adjust ranking resources. However, both empirical and theoretical analyses indicate that the previous item-level tax policy cannot meet two ideal controllable requirements: (1) continuity, ensuring minor changes in tax rates result in small accuracy and fairness shifts; (2) controllability over accuracy loss, ensuring precise estimation of the accuracy loss under a specific tax rate. To overcome these challenges, we introduce a new fair re-ranking method named Tax-rank, which levies taxes based on the difference in utility between two items. Then, we efficiently optimize such an objective by utilizing the Sinkhorn algorithm in optimal transport. Upon a comprehensive analysis, Our model Tax-rank offers a superior tax policy for fair re-ranking, theoretically demonstrating both continuity and controllability over accuracy loss. Experimental results show that Tax-rank outperforms all state-of-the-art baselines in terms of effectiveness and efficiency on recommendation and advertising tasks., Comment: Accepted in SIGIR 2024

Dental fluorosis is a chronic disease caused by long-term overconsumption of fluoride, which leads to changes in the appearance of tooth enamel. It is an important basis for early non-invasive diagnosis of endemic fluorosis. However, even dental professionals may not be able to accurately distinguish dental fluorosis and its severity based on tooth images. Currently, there is still a gap in research on applying deep learning to diagnosing dental fluorosis. Therefore, we construct the first open-source dental fluorosis image dataset (DFID), laying the foundation for deep learning research in this field. To advance the diagnosis of dental fluorosis, we propose a pioneering deep learning model called masked latent transformer with the random masking ratio (MLTrMR). MLTrMR introduces a mask latent modeling scheme based on Vision Transformer to enhance contextual learning of dental fluorosis lesion characteristics. Consisting of a latent embedder, encoder, and decoder, MLTrMR employs the latent embedder to extract latent tokens from the original image, whereas the encoder and decoder comprising the latent transformer (LT) block are used to process unmasked tokens and predict masked tokens, respectively. To mitigate the lack of inductive bias in Vision Transformer, which may result in performance degradation, the LT block introduces latent tokens to enhance the learning capacity of latent lesion features. Furthermore, we design an auxiliary loss function to constrain the parameter update direction of the model. MLTrMR achieves 80.19% accuracy, 75.79% F1, and 81.28% quadratic weighted kappa on DFID, making it state-of-the-art (SOTA).

Background and aimsPruritus is associated with multiple liver diseases, particularly those with cholestasis, but the mechanism remains incompletely understood. Our aim was to evaluate serum IL-31 as a putative biomarker of pruritus in clinical trials of an farnesoid X receptor (FXR) agonist, cilofexor, in patients with NASH, primary sclerosing cholangitis (PSC), and primary biliary cholangitis (PBC).Approach and resultsSerum IL-31 was measured in clinical studies of cilofexor in NASH, PSC, and PBC. In patients with PSC or PBC, baseline IL-31 was elevated compared to patients with NASH and healthy volunteers (HVs). IL-31 correlated with serum bile acids among patients with NASH, PBC, and PSC. Baseline IL-31 levels in PSC and PBC were positively correlated with Visual Analog Scale for pruritus and 5-D itch scores. In patients with NASH, cilofexor dose-dependently increased IL-31 from Week (W)1 to W24. In patients with NASH receiving cilofexor 100 mg, IL-31 was higher in those with Grade 2-3 pruritus adverse events (AEs) than those with Grade 0-1 pruritus AEs. IL-31 weakly correlated with C4 at baseline in patients with NASH, and among those receiving cilofexor 100 mg, changes in IL-31 and C4 from baseline to W24 were negatively correlated. IL-31 messenger RNA (mRNA) was elevated in hepatocytes from patients with PSC and NASH compared to HVs. In a humanized liver murine model, obeticholic acid increased IL-31 mRNA expression in human hepatocytes and serum levels of human IL-31.ConclusionsIL-31 levels correlate with pruritus in patients with cholestatic disease and NASH, with FXR agonist therapy resulting in higher serum levels in the latter group. IL-31 appears to derive in part from increased hepatocyte expression. These findings have therapeutic implications for patients with liver disease and pruritus.

While the use of machine translation (MT) in the classroom has been explored from various perspectives, the relationship between language proficiency and MT use regarding learners’ behaviors and beliefs remains unclear in the research literature. This study focused on four Japanese learners with various language proficiencies from a fourth-year Japanese language class (two advanced-level, one intermediate-high, and one novice-high level) and investigated how they edited self-written text with MT by examining the scope and types of revisions they made as well as their perceptions about using MT for editing. The data included four types of drafts of a writing assignment: (1) D1 (self-written drafts in Japanese without the help of MT); (2) D2 (revised corresponding drafts in L1 provided by MT); (3) D3 (drafts in Japanese provided by MT based on D2); (4) D4 (revised drafts based on comparison of D1 and D3) and their reflection papers. The results show that the four participants adopted various ways of editing self-written text. While all the participants’ revisions are at local levels, the two advanced level learners primarily focused on vocabulary revision while the other two learners’ revisions extended to the sentence level. The findings also show that the advanced-level and intermediate-high-level learners have various degrees of positive attitudes toward using MT. In contrast, while the positive effects of MT use are acknowledged, the novice-high level learner also feels ashamed and dishonest when using MT. This article concludes with insights that can assist instructors in facilitating MT as a pedagogical tool for language learning and teaching with diverse students.&nbsp