Search

LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain vulnerable to adversarial queries and the unlearned knowledge resurfaces after the manually designed attack queries. As part of a red-team effort to proactively assess the vulnerabilities of unlearned models, we design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack these models and evaluate their robustness. It optimizes adversarial suffixes to reintroduce the unlearned knowledge in various scenarios. We find that unlearned knowledge can be recovered in $55.2\%$ of the questions, even without revealing the unlearned model's parameters. In response to this vulnerability, we propose Latent Adversarial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. It formulates the unlearning process as a min-max optimization problem and resolves it through two stages: an attack stage, where perturbation vectors are trained and added to the latent space of LLMs to recover the unlearned knowledge, and a defense stage, where previously trained perturbation vectors are used to enhance unlearned model's robustness. With our LAU framework, we obtain two robust unlearning methods, AdvGA and AdvNPO. We conduct extensive experiments across multiple unlearning benchmarks and various models, and demonstrate that they improve the unlearning effectiveness by over $53.5\%$, cause only less than a $11.6\%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities., Comment: 13 pages

Knowledge editing aims to update outdated or incorrect knowledge in large language models (LLMs). However, current knowledge editing methods have limited scalability for lifelong editing. This study explores the fundamental reason why knowledge editing fails in lifelong editing. We begin with the closed-form solution derived from linear associative memory, which underpins state-of-the-art knowledge editing methods. We extend the solution from single editing to lifelong editing, and through rigorous mathematical derivation, identify an interference term in the final solution, suggesting that editing knowledge may impact irrelevant knowledge. Further analysis of the interference term reveals a close relationship with superposition between knowledge representations. When knowledge superposition does not exist in language models, the interference term vanishes, allowing for lossless knowledge editing. Experiments across numerous language models reveal that knowledge superposition is universal, exhibiting high kurtosis, zero mean, and heavy-tailed distributions with clear scaling laws. Ultimately, by combining theory and experiments, we demonstrate that knowledge superposition is the fundamental reason for the failure of lifelong editing. Moreover, this is the first study to investigate knowledge editing from the perspective of superposition and provides a comprehensive observation of superposition across numerous real-world language models. Code available at https://github.com/ChenhuiHu/knowledge_in_superposition.

Planning, as the core module of agents, is crucial in various fields such as embodied agents, web navigation, and tool using. With the development of large language models (LLMs), some researchers treat large language models as intelligent agents to stimulate and evaluate their planning capabilities. However, the planning mechanism is still unclear. In this work, we focus on exploring the look-ahead planning mechanism in large language models from the perspectives of information flow and internal representations. First, we study how planning is done internally by analyzing the multi-layer perception (MLP) and multi-head self-attention (MHSA) components at the last token. We find that the output of MHSA in the middle layers at the last token can directly decode the decision to some extent. Based on this discovery, we further trace the source of MHSA by information flow, and we reveal that MHSA mainly extracts information from spans of the goal states and recent steps. According to information flow, we continue to study what information is encoded within it. Specifically, we explore whether future decisions have been encoded in advance in the representation of flow. We demonstrate that the middle and upper layers encode a few short-term future decisions to some extent when planning is successful. Overall, our research analyzes the look-ahead planning mechanisms of LLMs, facilitating future research on LLMs performing planning tasks.

Large language models (LLMs) have achieved remarkable success but still tend to generate factually erroneous responses, a phenomenon known as hallucination. A recent trend is to use preference learning to fine-tune models to align with factuality. However, existing work primarily evaluates fine-tuned models on in-domain (ID) datasets and the factuality on out-of-domain (OOD) datasets remains underexplored. In this paper, we conduct a comprehensive evaluation of the factuality of different models tuned by various preference learning algorithms and demonstrate that their performance on OOD datasets either increases minimally or decreases. Subsequently, we reveal that the main cause of model's failure to uphold factuality under a distribution shift is \textbf{under-alignment}, rather than \textbf{over-alignment}, by analyzing the token distribution shift of the models before and after tuning. Finally, we propose \textbf{APEFT} (\textbf{A}tomic \textbf{P}reference \textbf{E}nhanced \textbf{F}actuality \textbf{T}uning), a framework that enhances model's awareness of factuality at the granularity of individual facts. Extensive experiments demonstrate that APEFT improves model performance by an average of $\boldsymbol{3.45\%}$ on both ID and OOD datasets, which is highly effective.

Knowledge editing aims to adjust the knowledge within large language models (LLMs) to prevent their responses from becoming obsolete or inaccurate. However, existing works on knowledge editing are primarily conducted in a single language, which is inadequate for multilingual language models. In this paper, we focus on multilingual knowledge editing (MKE), which requires propagating updates across multiple languages. This necessity poses a significant challenge for the task. Furthermore, the limited availability of a comprehensive dataset for MKE exacerbates this challenge, hindering progress in this area. Hence, we introduce the Multilingual Knowledge Editing Benchmark (MKEB), a novel dataset comprising 12 languages and providing a complete evaluation framework. Additionally, we propose a method that enhances Multilingual knowledge Editing with neuron-Masked Low-Rank Adaptation (MEMLA). Specifically, we identify two categories of knowledge neurons to improve editing precision. Moreover, we perform LoRA-based editing with neuron masks to efficiently modify parameters and facilitate the propagation of updates across multiple languages. Experiments demonstrate that our method outperforms existing baselines and significantly enhances the multi-hop reasoning capability of the edited model, with minimal impact on its downstream task performance. The dataset and code will be made publicly available.

Large language models (LLMs) inevitably memorize sensitive, copyrighted, and harmful knowledge from the training corpus; therefore, it is crucial to erase this knowledge from the models. Machine unlearning is a promising solution for efficiently removing specific knowledge by post hoc modifying models. In this paper, we propose a Real-World Knowledge Unlearning benchmark (RWKU) for LLM unlearning. RWKU is designed based on the following three key factors: (1) For the task setting, we consider a more practical and challenging unlearning setting, where neither the forget corpus nor the retain corpus is accessible. (2) For the knowledge source, we choose 200 real-world famous people as the unlearning targets and show that such popular knowledge is widely present in various LLMs. (3) For the evaluation framework, we design the forget set and the retain set to evaluate the model's capabilities across various real-world applications. Regarding the forget set, we provide four four membership inference attack (MIA) methods and nine kinds of adversarial attack probes to rigorously test unlearning efficacy. Regarding the retain set, we assess locality and utility in terms of neighbor perturbation, general ability, reasoning ability, truthfulness, factuality, and fluency. We conduct extensive experiments across two unlearning scenarios, two models and six baseline methods and obtain some meaningful findings. We release our benchmark and code publicly at http://rwku-bench.github.io for future work., Comment: 48 pages, 7 figures, 12 tables

Large language models (LLMs) suffer from serious unfaithful chain-of-thought (CoT) issues. Previous work attempts to measure and explain it but lacks in-depth analysis within CoTs and does not consider the interactions among all reasoning components jointly. In this paper, we first study the CoT faithfulness issue at the granularity of CoT steps, identify two reasoning paradigms: centralized reasoning and distributed reasoning, and find their relationship with faithfulness. Subsequently, we conduct a joint analysis of the causal relevance among the context, CoT, and answer during reasoning. The result proves that, when the LLM predicts answers, it can recall correct information missing in the CoT from the context, leading to unfaithfulness issues. Finally, we propose the inferential bridging method to mitigate this issue, in which we use the attribution method to recall information as hints for CoT generation and filter out noisy CoTs based on their semantic consistency and attribution scores. Extensive experiments demonstrate that our approach effectively alleviates the unfaithful CoT problem., Comment: 25 pages, under review

Large language models (LLMs) store extensive factual knowledge, but the mechanisms behind how they store and express this knowledge remain unclear. The Knowledge Neuron (KN) thesis is a prominent theory for explaining these mechanisms. This theory is based on the knowledge localization (KL) assumption, which suggests that a fact can be localized to a few knowledge storage units, namely knowledge neurons. However, this assumption may be overly strong regarding knowledge storage and neglects knowledge expression mechanisms. Thus, we re-examine the KL assumption and confirm the existence of facts that do not adhere to it from both statistical and knowledge modification perspectives. Furthermore, we propose the Query Localization (QL) assumption. (1) Query-KN Mapping: The localization results are associated with the query rather than the fact. (2) Dynamic KN Selection: The attention module contributes to the selection of KNs for answering a query. Based on this, we further propose the Consistency-Aware KN modification method, which improves the performance of knowledge modification. We conduct 39 sets of experiments, along with additional visualization experiments, to rigorously validate our conclusions.

Traditional continual event detection relies on abundant labeled data for training, which is often impractical to obtain in real-world applications. In this paper, we introduce continual few-shot event detection (CFED), a more commonly encountered scenario when a substantial number of labeled samples are not accessible. The CFED task is challenging as it involves memorizing previous event types and learning new event types with few-shot samples. To mitigate these challenges, we propose a memory-based framework: Hierarchical Augmentation Networks (HANet). To memorize previous event types with limited memory, we incorporate prototypical augmentation into the memory set. For the issue of learning new event types in few-shot scenarios, we propose a contrastive augmentation module for token representations. Despite comparing with previous state-of-the-art methods, we also conduct comparisons with ChatGPT. Experiment results demonstrate that our method significantly outperforms all of these methods in multiple continual few-shot event detection tasks., Comment: Accepted to LREC-COLING 2024

With the development of deep learning, natural language processing technology has effectively improved the efficiency of various aspects of the traditional judicial industry. However, most current efforts focus solely on individual judicial stage, overlooking cross-stage collaboration. As the autonomous agents powered by large language models are becoming increasingly smart and able to make complex decisions in real-world settings, offering new insights for judicial intelligence. In this paper, (1) we introduce SimuCourt, a judicial benchmark that encompasses 420 judgment documents from real-world, spanning the three most common types of judicial cases, and a novel task Judicial Decision-Making to evaluate the judicial analysis and decision-making power of agents. To support this task, we construct a large-scale judicial knowledge base, JudicialKB, with multiple legal knowledge. (2) we propose a novel multi-agent framework, AgentsCourt. Our framework follows the real-world classic court trial process, consisting of court debate simulation, legal information retrieval and judgement refinement to simulate the decision-making of judge. (3) we perform extensive experiments, the results demonstrate that, our framework outperforms the existing advanced methods in various aspects, especially in generating legal grounds, where our model achieves significant improvements of 8.6% and 9.1% F1 score in the first and second instance settings, respectively.

Event Causality Identification (ECI) refers to the detection of causal relations between events in texts. However, most existing studies focus on sentence-level ECI with high-resource languages, leaving more challenging document-level ECI (DECI) with low-resource languages under-explored. In this paper, we propose a Heterogeneous Graph Interaction Model with Multi-granularity Contrastive Transfer Learning (GIMC) for zero-shot cross-lingual document-level ECI. Specifically, we introduce a heterogeneous graph interaction network to model the long-distance dependencies between events that are scattered over a document. Then, to improve cross-lingual transferability of causal knowledge learned from the source language, we propose a multi-granularity contrastive transfer learning module to align the causal representations across languages. Extensive experiments show our framework outperforms the previous state-of-the-art model by 9.4% and 8.2% of average F1 score on monolingual and multilingual scenarios respectively. Notably, in the multilingual scenario, our zero-shot framework even exceeds GPT-3.5 with few-shot learning by 24.3% in overall performance., Comment: Accepted at LREC-COLING 2024

Large Language Models (LLMs) have shown impressive capabilities but still suffer from the issue of hallucinations. A significant type of this issue is the false premise hallucination, which we define as the phenomenon when LLMs generate hallucinated text when confronted with false premise questions. In this paper, we perform a comprehensive analysis of the false premise hallucination and elucidate its internal working mechanism: a small subset of attention heads (which we designate as false premise heads) disturb the knowledge extraction process, leading to the occurrence of false premise hallucination. Based on our analysis, we propose \textbf{FAITH} (\textbf{F}alse premise \textbf{A}ttention head constra\textbf{I}ining for mi\textbf{T}igating \textbf{H}allucinations), a novel and effective method to mitigate false premise hallucinations. It constrains the false premise attention heads during the model inference process. Impressively, extensive experiments demonstrate that constraining only approximately $1\%$ of the attention heads in the model yields a notable increase of nearly $20\%$ of model performance., Comment: 12 pages, 5 figures, 5 tables

Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). However, we find these CoT-like methods lead to a considerable number of originally correct answers turning wrong, which we define as the Toxic CoT problem. To interpret and mitigate this problem, we first utilize attribution tracing and causal tracing methods to probe the internal working mechanism of the LLM during CoT reasoning. Through comparisons, we prove that the model exhibits information loss from the question over the shallow attention layers when generating rationales or answers. Based on the probing findings, we design a novel method called RIDERS (Residual decodIng and sERial-position Swap), which compensates for the information deficit in the model from both decoding and serial-position perspectives. Through extensive experiments on multiple commonsense reasoning benchmarks, we validate that this method not only significantly eliminates Toxic CoT problems (decreased by 23.6%), but also effectively improves the model's overall commonsense reasoning performance (increased by 5.5%)., Comment: Accepted as a long paper to ACL 2024 Main, 25 pages, 22 figures

Recently, retrieval augmentation and tool augmentation have demonstrated a remarkable capability to expand the internal memory boundaries of language models (LMs) by providing external context. However, internal memory and external context inevitably clash, leading to knowledge conflicts within LMs. In this paper, we aim to interpret the mechanism of knowledge conflicts through the lens of information flow, and then mitigate conflicts by precise interventions at the pivotal point. We find there are some attention heads with opposite effects in the later layers, where memory heads can recall knowledge from internal memory, and context heads can retrieve knowledge from external context. Moreover, we reveal that the pivotal point at which knowledge conflicts emerge in LMs is the integration of inconsistent information flows by memory heads and context heads. Inspired by the insights, we propose a novel method called Pruning Head via PatH PatcHing (PH3), which can efficiently mitigate knowledge conflicts by pruning conflicting attention heads without updating model parameters. PH3 can flexibly control eight LMs to use internal memory ($\uparrow$ 44.0%) or external context ($\uparrow$ 38.5%). Moreover, PH3 can also improve the performance of LMs on open-domain QA tasks. We also conduct extensive experiments to demonstrate the cross-model, cross-relation, and cross-format generalization of our method., Comment: 21 pages, 42 figures, 4 tables

Retrieval-augmented language models (RALMs) have demonstrated significant potential in refining and expanding their internal memory by retrieving evidence from external sources. However, RALMs will inevitably encounter knowledge conflicts when integrating their internal memory with external sources. Knowledge conflicts can ensnare RALMs in a tug-of-war between knowledge, limiting their practical applicability. In this paper, we focus on exploring and resolving knowledge conflicts in RALMs. First, we present an evaluation framework for assessing knowledge conflicts across various dimensions. Then, we investigate the behavior and preference of RALMs from the following two perspectives: (1) Conflicts between internal memory and external sources: We find that stronger RALMs emerge with the Dunning-Kruger effect, persistently favoring their faulty internal memory even when correct evidence is provided. Besides, RALMs exhibit an availability bias towards common knowledge; (2) Conflicts between truthful, irrelevant and misleading evidence: We reveal that RALMs follow the principle of majority rule, leaning towards placing trust in evidence that appears more frequently. Moreover, we find that RALMs exhibit confirmation bias, and are more willing to choose evidence that is consistent with their internal memory. To solve the challenge of knowledge conflicts, we propose a method called Conflict-Disentangle Contrastive Decoding (CD2) to better calibrate the model's confidence. Experimental results demonstrate that our CD2 can effectively resolve knowledge conflicts in RALMs., Comment: Accepted at LREC-COLING 2024

Large language models (LLMs) store extensive factual knowledge, but the underlying mechanisms remain unclear. Previous research suggests that factual knowledge is stored within multi-layer perceptron weights, and some storage units exhibit degeneracy, referred to as Degenerate Knowledge Neurons (DKNs). Despite the novelty and unique properties of this concept, it has not been rigorously defined or systematically studied. We first consider the connection weight patterns of MLP neurons and define DKNs from both structural and functional aspects. Based on this, we introduce the Neurological Topology Clustering method, which allows the formation of DKNs in any numbers and structures, leading to a more accurate DKN acquisition. Furthermore, inspired by cognitive science, we explore the relationship between DKNs and the robustness, evolvability, and complexity of LLMs. Our execution of 34 experiments under 6 settings demonstrates the connection between DKNs and these three properties. The code will be available soon.

Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without costly retraining for outdated or erroneous knowledge. However, current knowledge editing methods primarily focus on single editing, failing to meet the requirements for lifelong editing. This study reveals a performance degradation encountered by knowledge editing in lifelong editing, characterized by toxicity buildup and toxicity flash, with the primary cause identified as pattern unmatch. We introduce a knowledge editing approach named Wise-Layer Knowledge Editor (WilKE), which selects editing layer based on the pattern matching degree of editing knowledge across different layers in language models. Experimental results demonstrate that, in lifelong editing, WilKE exhibits an average improvement of 46.2% and 67.8% on editing GPT2-XL and GPT-J relative to state-of-the-art knowledge editing methods., Comment: To be published in ACL Findings 2024

Data is one of the most critical elements in building a large language model. However, existing systems either fail to customize a corpus curation pipeline or neglect to leverage comprehensive corpus assessment for iterative optimization of the curation. To this end, we present a pretraining corpus curation and assessment platform called Oasis -- a one-stop system for data quality improvement and quantification with user-friendly interactive interfaces. Specifically, the interactive modular rule filter module can devise customized rules according to explicit feedback. The debiased neural filter module builds the quality classification dataset in a negative-centric manner to remove the undesired bias. The adaptive document deduplication module could execute large-scale deduplication with limited memory resources. These three parts constitute the customized data curation module. And in the holistic data assessment module, a corpus can be assessed in local and global views, with three evaluation means including human, GPT-4, and heuristic metrics. We exhibit a complete process to use Oasis for the curation and assessment of pretraining data. In addition, an 800GB bilingual corpus curated by Oasis is publicly released.

Knowledge-based visual question answering is a very challenging and widely concerned task. Previous methods adopts the implicit knowledge in large language models (LLM) to achieve excellent results, but we argue that existing methods may suffer from biasing understanding of the image and insufficient knowledge to solve the problem. In this paper, we propose PROOFREAD -PROmpting vision language model with knOwledge From laRgE lAnguage moDel, a novel, lightweight and efficient kowledge-based VQA framework, which make the vision language model and the large language model cooperate to give full play to their respective strengths and bootstrap each other. In detail, our proposed method uses LLM to obtain knowledge explicitly, uses the vision language model which can see the image to get the knowledge answer, and introduces knowledge perceiver to filter out knowledge that is harmful for getting the correct final answer. Experimental results on two datasets prove the effectiveness of our approach. Our method outperforms all state-of-the-art methods on the A-OKVQA dataset in two settings and also achieves relatively good performance on the OKVQA dataset.

The unprecedented performance of large language models (LLMs) requires comprehensive and accurate evaluation. We argue that for LLMs evaluation, benchmarks need to be comprehensive and systematic. To this end, we propose the ZhuJiu benchmark, which has the following strengths: (1) Multi-dimensional ability coverage: We comprehensively evaluate LLMs across 7 ability dimensions covering 51 tasks. Especially, we also propose a new benchmark that focuses on knowledge ability of LLMs. (2) Multi-faceted evaluation methods collaboration: We use 3 different yet complementary evaluation methods to comprehensively evaluate LLMs, which can ensure the authority and accuracy of the evaluation results. (3) Comprehensive Chinese benchmark: ZhuJiu is the pioneering benchmark that fully assesses LLMs in Chinese, while also providing equally robust evaluation abilities in English. (4) Avoiding potential data leakage: To avoid data leakage, we construct evaluation data specifically for 37 tasks. We evaluate 10 current mainstream LLMs and conduct an in-depth discussion and analysis of their results. The ZhuJiu benchmark and open-participation leaderboard are publicly released at http://www.zhujiu-benchmark.com/ and we also provide a demo video at https://youtu.be/qypkJ89L1Ic.

Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in multilingual PLMs, and introduces the Architecture-adapted Multilingual Integrated Gradients method, which successfully localizes knowledge neurons more precisely compared to current methods, and is more universal across various architectures and languages. Moreover, we conduct an in-depth exploration of knowledge neurons, leading to the following two important discoveries: (1) The discovery of Language-Independent Knowledge Neurons, which store factual knowledge in a form that transcends language. We design cross-lingual knowledge editing experiments, demonstrating that the PLMs can accomplish this task based on language-independent neurons; (2) The discovery of Degenerate Knowledge Neurons, a novel type of neuron showing that different knowledge neurons can store the same fact. Its property of functional overlap endows the PLMs with a robust mastery of factual knowledge. We design fact-checking experiments, proving that the degenerate knowledge neurons can help the PLMs to detect wrong facts. Experiments corroborate these findings, shedding light on the mechanisms of factual knowledge storage in multilingual PLMs, and contribute valuable insights to the field. The code is available at https://github.com/heng840/AMIG., Comment: Accepted in the 38th AAAI Conference on Artificial Intelligence (AAAI 2024)

Modern models for event causality identification (ECI) are mainly based on supervised learning, which are prone to the data lacking problem. Unfortunately, the existing NLP-related augmentation methods cannot directly produce the available data required for this task. To solve the data lacking problem, we introduce a new approach to augment training data for event causality identification, by iteratively generating new examples and classifying event causality in a dual learning framework. On the one hand, our approach is knowledge-guided, which can leverage existing knowledge bases to generate well-formed new sentences. On the other hand, our approach employs a dual mechanism, which is a learnable augmentation framework and can interactively adjust the generation process to generate task-related sentences. Experimental results on two benchmarks EventStoryLine and Causal-TimeBank show that 1) our method can augment suitable task-related training data for ECI; 2) our method outperforms previous methods on EventStoryLine and Causal-TimeBank (+2.5 and +2.1 points on F1 value respectively)., Comment: Accepted to ACL 2021

Current models for event causality identification (ECI) mainly adopt a supervised framework, which heavily rely on labeled data for training. Unfortunately, the scale of current annotated datasets is relatively limited, which cannot provide sufficient support for models to capture useful indicators from causal statements, especially for handing those new, unseen cases. To alleviate this problem, we propose a novel approach, shortly named CauSeRL, which leverages external causal statements for event causality identification. First of all, we design a self-supervised framework to learn context-specific causal patterns from external causal statements. Then, we adopt a contrastive transfer strategy to incorporate the learned context-specific causal patterns into the target ECI model. Experimental results show that our method significantly outperforms previous methods on EventStoryLine and Causal-TimeBank (+2.0 and +3.4 points on F1 value respectively)., Comment: Accepted to Findings of ACL 2021