Search

The 1st Workshop on Data Contamination (CONDA 2024) focuses on all relevant aspects of data contamination in natural language processing, where data contamination is understood as situations where evaluation data is included in pre-training corpora used to train large scale models, compromising evaluation results. The workshop fostered a shared task to collect evidence on data contamination in current available datasets and models. The goal of the shared task and associated database is to assist the community in understanding the extent of the problem and to assist researchers in avoiding reporting evaluation results on known contaminated resources. The shared task provides a structured, centralized public database for the collection of contamination evidence, open to contributions from the community via GitHub pool requests. This first compilation paper is based on 566 reported entries over 91 contaminated sources from a total of 23 contributors. The details of the individual contamination events are available in the platform. The platform continues to be online, open to contributions from the community., Comment: https://huggingface.co/spaces/CONDA-Workshop/Data-Contamination-Database

Simultaneous imaging of fluorescence-labeled and label-free phase objects in the same sample provides distinct and complementary information. Most multimodal fluorescence-phase imaging operates in transmission mode, capturing fluorescence images and phase images separately or sequentially, which limits their practical application in vivo. Here, we develop fluorescence diffraction tomography (FDT) with explicit neural fields to reconstruct the 3D refractive index (RI) of phase objects from diffracted fluorescence images captured in reflection mode. The successful reconstruction of 3D RI using FDT relies on four key components: a coarse-to-fine structure, self-calibration, a differential multi-slice rendering model, and partially coherent masks. The explicit representation integrates with the coarse-to-fine structure for high-speed, high-resolution reconstruction, while the differential multi-slice rendering model enables self-calibration of fluorescence illumination, ensuring accurate forward image prediction and RI reconstruction. Partially coherent masks efficiently resolve discrepancies between the coherent light model and partially coherent light data. FDT successfully reconstructs the RI of 3D cultured label-free bovine myotubes in a 530 $\times$ 530 $\times$ 300 $\mu m^3$ volume at 1024 $\times$ 1024 pixels across 24 $z$-layers from fluorescence images, demonstrating high resolution and high accuracy 3D RI reconstruction of bulky and heterogeneous biological samples in vitro.

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention computation, it takes 30 minutes for an 8B LLM to process a prompt of 1M tokens (i.e., the pre-filling stage) on a single A100 GPU. Existing methods for speeding up prefilling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs. To address this gap, we introduce MInference (Milliontokens Inference), a sparse calculation method designed to accelerate pre-filling of long-sequence processing. Specifically, we identify three unique patterns in long-context attention matrices-the A-shape, Vertical-Slash, and Block-Sparsethat can be leveraged for efficient sparse computation on GPUs. We determine the optimal pattern for each attention head offline and dynamically build sparse indices based on the assigned pattern during inference. With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs. Our proposed technique can be directly applied to existing LLMs without any modifications to the pre-training setup or additional fine-tuning. By evaluating on a wide range of downstream tasks, including InfiniteBench, RULER, PG-19, and Needle In A Haystack, and models including LLaMA-3-1M, GLM4-1M, Yi-200K, Phi-3-128K, and Qwen2-128K, we demonstrate that MInference effectively reduces inference latency by up to 10x for pre-filling on an A100, while maintaining accuracy. Our code is available at https://aka.ms/MInference.

In recent years, open-pit mining has seen significant advancement, the cooperative operation of various specialized machinery substantially enhancing the efficiency of mineral extraction. However, the harsh environment and complex conditions in open-pit mines present substantial challenges for the implementation of autonomous transportation systems. This research introduces a novel paradigm that integrates Scenario Engineering (SE) with autonomous transportation systems to significantly improve the trustworthiness, robustness, and efficiency in open-pit mines by incorporating the four key components of SE, including Scenario Feature Extractor, Intelligence and Index (I&I), Calibration and Certification (C&C), and Verification and Validation (V&V). This paradigm has been validated in two famous open-pit mines, the experiment results demonstrate marked improvements in robustness, trustworthiness, and efficiency. By enhancing the capacity, scalability, and diversity of autonomous transportation, this paradigm fosters the integration of SE and parallel driving and finally propels the achievement of the '6S' objectives., Comment: 11 Pages, 7 Figures

Existing methods for evaluating large language models face challenges such as data contamination, sensitivity to prompts, and the high cost of benchmark creation. To address this, we propose a lossless data compression based evaluation approach that tests how models' predictive abilities generalize after their training cutoff. Specifically, we collect comprehensive test data spanning 83 months from 2017 to 2023 and split the data into training and testing periods according to models' training data cutoff. We measure: 1) the compression performance on the testing period as a measure of generalization on unseen data; and 2) the performance gap between the training and testing period as a measure of robustness. Our experiments test 14 representative large language models with various sizes on sources including Wikipedia, news articles, code, arXiv papers, and multi-modal data. We find that the compression rate of many models reduces significantly after their cutoff date, but models such as Mistral and Llama-2 demonstrate a good balance between performance and robustness. Results also suggest that models struggle to generalize on news and code data, but work especially well on arXiv papers. We also find the context size and tokenization implementation have a big impact of on the overall compression performance.

Metaphors are considered to pose challenges for a wide spectrum of NLP tasks. This gives rise to the area of computational metaphor processing. However, it remains unclear what types of metaphors challenge current state-of-the-art models. In this paper, we test various NLP models on the VUA metaphor dataset and quantify to what extent metaphors affect models' performance on various downstream tasks. Analysis reveals that VUA includes a large number of metaphors that pose little difficulty to downstream tasks. We would like to shift the attention of researchers away from these metaphors to instead focus on challenging metaphors. To identify hard metaphors, we propose an automatic pipeline that identifies metaphors that challenge a particular model. Our analysis demonstrates that our detected hard metaphors contrast significantly with VUA and reduce the accuracy of machine translation by 16\%, QA performance by 4\%, NLI by 7\%, and metaphor identification recall by over 14\% for various popular NLP systems.

Light penetration depth in biological tissue is limited by tissue scattering. There is an urgent need for scattering compensation in vivo focusing and imaging, particularly challenging in photon-starved scenarios, without access to the transmission side of the scattering tissue. Here, we introduce a two-photon microscopy system with Fourier-domain open-channel coupling for scattering correction (2P-FOCUS). 2P-FOCUS corrects scattering by utilizing the non-linearity of multiple-beam interference and two-photon excitation, eliminating the need for a guide star, iterative optimization, or measuring transmission or reflection matrices. We demonstrate that 2P-FOCUS significantly enhances two-photon fluorescence signals by several tens of folds when focusing through a bone sample, compared to cases without scattering compensation at equivalent excitation power. We also show that 2P-FOCUS can correct scattering over large volumes by imaging neurons and cerebral blood vessels within a 230x230x500 um\textsuperscript{3} volume in the mouse brain in vitro. 2P-FOCUS could serve as a powerful tool for deep tissue imaging in bulky organisms or live animals.

Data contamination in evaluation is getting increasingly prevalent with the emergence of language models pre-trained on super large, automatically crawled corpora. This problem leads to significant challenges in the accurate assessment of model capabilities and generalisations. In this paper, we propose LatestEval, an automatic method that leverages the most recent texts to create uncontaminated reading comprehension evaluations. LatestEval avoids data contamination by only using texts published within a recent time window, ensuring no overlap with the training corpora of pre-trained language models. We develop the LatestEval automated pipeline to 1) gather the latest texts; 2) identify key information, and 3) construct questions targeting the information while removing the existing answers from the context. This encourages models to infer the answers themselves based on the remaining context, rather than just copy-paste. Our experiments demonstrate that language models exhibit negligible memorisation behaviours on LatestEval as opposed to previous benchmarks, suggesting a significantly reduced risk of data contamination and leading to a more robust evaluation. Data and code are publicly available at: https://github.com/liyucheng09/LatestEval., Comment: AAAI 2024

Data contamination in model evaluation has become increasingly prevalent with the growing popularity of large language models. It allows models to "cheat" via memorisation instead of displaying true capabilities. Therefore, contamination analysis has become an crucial part of reliable model evaluation to validate results. However, existing contamination analysis is usually conducted internally by large language model developers and often lacks transparency and completeness. This paper presents an extensive data contamination report for over 15 popular large language models across six popular multiple-choice QA benchmarks. We also introduce an open-source pipeline that enables the community to perform contamination analysis on customised data and models. Our experiments reveal varying contamination levels ranging from 1\% to 45\% across benchmarks, with the contamination degree increasing rapidly over time. Performance analysis of large language models indicates that data contamination does not necessarily lead to increased model metrics: while significant accuracy boosts of up to 14\% and 7\% are observed on contaminated C-Eval and Hellaswag benchmarks, only a minimal increase is noted on contaminated MMLU. We also find larger models seem able to gain more advantages than smaller models on contaminated test sets.

Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in memory and inference time, and potential context truncation when the input exceeds the LLM's fixed context length. This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact. We test our approach using common data sources requiring long context processing: arXiv papers, news articles, and long conversations, on tasks of summarisation, question answering, and response generation. Experimental results show that Selective Context significantly reduces memory cost and decreases generation latency while maintaining comparable performance compared to that achieved when full context is used. Specifically, we achieve a 50\% reduction in context cost, resulting in a 36\% reduction in inference memory usage and a 32\% reduction in inference time, while observing only a minor drop of .023 in BERTscore and .038 in faithfulness on four downstream applications, indicating that our method strikes a good balance between efficiency and performance., Comment: EMNLP 2023. arXiv admin note: substantial text overlap with arXiv:2304.12102; text overlap with arXiv:2303.11076 by other authors

Data contamination in model evaluation is getting increasingly prevalent as the massive training corpora of large language models often unintentionally include benchmark samples. Therefore, contamination analysis has became an inevitable part of reliable model evaluation. However, existing method of contamination analysis requires the access of the entire training data which is often confidential for recent models. This prevent the community to rigorously audit these models and conduct accurate assessment of their capability. In this paper, we propose a novel method to quantify contamination without the access of the full training set, that measure the extent of contamination with perplexity. Our analysis provides evidence of significant memorisation of recent foundation models in popular reading comprehension, summarisation benchmarks, while multiple choice appears less contaminated.

Autonomous driving vehicles aim to free the hands of vehicle operators, helping them to drive easier and faster, meanwhile, improving the safety of driving on the highway or in complex scenarios. Automated driving systems (ADS) are developed and designed in the last several decades to realize fully autonomous driving vehicles (L4 or L5 level). The scale of sampling space leads to the main computational complexity. Therefore, by adjusting the sampling method, the difficulty to solve the real-time motion planning problem could be incrementally reduced. Usually, the Average Sampling Method is taken in Lattice Planner, and Random Sampling Method is chosen for RRT algorithms. However, both of them don't take into consideration the prior information, and focus the sampling space on areas where the optimal trajectory is previously obtained. Therefore, \emph{in this thesis it is proposed an adaptive sampling method to reduce the computation complexity, and achieve faster solutions while keeping the quality of optimal solution unchanged}. The main contribution of this thesis is the significant decrease in the complexity of the optimization problem for motion planning, without sacrificing the quality of the final trajectory output, with the implementation of an Adaptive Sampling method based on Artificial Potential Field (ASAPF). In addition, also the quality and the stability of the trajectory is improved due to the appropriate sampling of the appropriate region to be analyzed., Comment: Master's thesis

One noticeable trend in metaphor detection is the embrace of linguistic theories such as the metaphor identification procedure (MIP) for model architecture design. While MIP clearly defines that the metaphoricity of a lexical unit is determined based on the contrast between its \textit{contextual meaning} and its \textit{basic meaning}, existing work does not strictly follow this principle, typically using the \textit{aggregated meaning} to approximate the basic meaning of target words. In this paper, we propose a novel metaphor detection method, which models the basic meaning of the word based on literal annotation from the training set, and then compares this with the contextual meaning in a target sentence to identify metaphors. Empirical results show that our method outperforms the state-of-the-art method significantly by 1.0\% in F1 score. Moreover, our performance even reaches the theoretical upper bound on the VUA18 benchmark for targets with basic annotations, which demonstrates the importance of modelling basic meanings for metaphor detection., Comment: ACL 2023

Large language models (LLMs) have received significant attention by achieving remarkable performance across various tasks. However, their fixed context length poses challenges when processing long documents or maintaining extended conversations. This paper proposes a method called \textit{Selective Context} that employs self-information to filter out less informative content, thereby enhancing the efficiency of the fixed context length. We demonstrate the effectiveness of our approach on tasks of summarisation and question answering across different data sources, including academic papers, news articles, and conversation transcripts.

We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection. Compared to existing models, RoPPT focuses on semantically relevant information and achieves the state-of-the-art on several main metaphor datasets. We also compare our approach against several popular denoising and pruning methods, demonstrating the effectiveness of our approach in context denoising. Our code and dataset can be found at https://github.com/MajiBear000/RoPPT

In this paper, we propose FrameBERT, a RoBERTa-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection. FrameBERT not only achieves better or comparable performance to the state-of-the-art, but also is more explainable and interpretable compared to existing models, attributing to its ability of accounting for external knowledge of FrameNet.

Metaphors are proven to have stronger emotional impact than literal expressions. Although this conclusion is shown to be promising in benefiting various NLP applications, the reasons behind this phenomenon are not well studied. This paper conducts the first study in exploring how metaphors convey stronger emotion than their literal counterparts. We find that metaphors are generally more specific than literal expressions. The more specific property of metaphor can be one of the reasons for metaphors' superiority in emotion expression. When we compare metaphors with literal expressions with the same specificity level, the gap of emotion expressing ability between both reduces significantly. In addition, we observe specificity is crucial in literal language as well, as literal language can express stronger emotion by making it more specific., Comment: FigLang@EMNLP2022

Metaphor generation is a challenging task which can impact many downstream tasks such as improving user satisfaction with dialogue systems and story generation. This paper tackles the problem of Chinese nominal metaphor generation by introducing a multitask metaphor generation framework with self-training and metaphor identification mechanisms. Self-training addresses the data scarcity issue of metaphor datasets. That is, instead of solely relying on labelled metaphor datasets which are usually small in size, self-training helps identify potential metaphors from a large-scale unlabelled corpus for metaphor generation. The metaphor weighting mechanism enables our model to focus on the metaphor-related parts of the input (e.g., the comparison of the metaphor and comparator) during model learning and thus improves the metaphoricity of the generated metaphors. Our model is trained on an annotated corpus consisting of 6.3k sentences that contain diverse metaphorical expressions. Experimental results show that our model is able to generate metaphors with better readability and creativity compared to the baseline models, even in the situation where training data is insufficient.

Recommender retrievers aim to rapidly retrieve a fraction of items from the entire item corpus when a user query requests, with the representative two-tower model trained with the log softmax loss. For efficiently training recommender retrievers on modern hardwares, inbatch sampling, where the items in the mini-batch are shared as negatives to estimate the softmax function, has attained growing interest. However, existing inbatch sampling based strategies just correct the sampling bias of inbatch items with item frequency, being unable to distinguish the user queries within the mini-batch and still incurring significant bias from the softmax. In this paper, we propose a Cache-Augmented Inbatch Importance Resampling (XIR) for training recommender retrievers, which not only offers different negatives to user queries with inbatch items, but also adaptively achieves a more accurate estimation of the softmax distribution. Specifically, XIR resamples items for the given mini-batch training pairs based on certain probabilities, where a cache with more frequently sampled items is adopted to augment the candidate item set, with the purpose of reusing the historical informative samples. XIR enables to sample query-dependent negatives based on inbatch items and to capture dynamic changes of model training, which leads to a better approximation of the softmax and further contributes to better convergence. Finally, we conduct experiments to validate the superior performance of the proposed XIR compared with competitive approaches., Comment: 18 pages