3 citations · 29 across the 53 of their papers we have counts for
26 papers · 1 filter
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
Zhuoran Jin, Hongbang Yuan, Tianyi Men +4
Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overl…
One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models
Pengfei Cao, Yuheng Chen, Zhuoran Jin +3
Large language models (LLMs) have learned vast amounts of factual knowledge through self-supervised pre-training on large-scale corpora. Meanwhile, LLMs have also demonstrated exce…
DTELS: Towards Dynamic Granularity of Timeline Summarization
Chenlong Zhang, Tong Zhou, Pengfei Cao +4
The rapid proliferation of online news has posed significant challenges in tracking the continuous development of news topics. Traditional timeline summarization constructs a chron…
LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning
Jiachun Li, Pengfei Cao, Chenhao Wang +6
Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of them. Researchers typically address these issues b…
A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns
Tianyi Men, Pengfei Cao, Zhuoran Jin +3
With the development of large language models, they are widely used as agents in various fields. A key component of agents is memory, which stores vital information but is suscepti…
MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models
Jiachun Li, Pengfei Cao, Zhuoran Jin +3
Inductive reasoning is an essential capability for large language models (LLMs) to achieve higher intelligence, which requires the model to generalize rules from observed facts and…
Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
Hongbang Yuan, Zhuoran Jin, Pengfei Cao +3
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 be…
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
Chenhui Hu, Pengfei Cao, Yubo Chen +2
Knowledge editing aims to update outdated or incorrect knowledge in large language models (LLMs). However, current knowledge editing methods have limited scalability for lifelong e…
Citekit: A Modular Toolkit for Large Language Model Citation Generation
Jiajun Shen, Tong Zhou, Yubo Chen +1
Enabling Large Language Models (LLMs) to generate citations in Question-Answering (QA) tasks is an emerging paradigm aimed at enhancing the verifiability of their responses when LL…
Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models
Hongbang Yuan, Yubo Chen, Pengfei Cao +3
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 us…
CogMG: Collaborative Augmentation Between Large Language Model and Knowledge Graph
Tong Zhou, Yubo Chen, Kang Liu +1
Large language models have become integral to question-answering applications despite their propensity for generating hallucinations and factually inaccurate content. Querying know…
Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models
Tianyi Men, Pengfei Cao, Zhuoran Jin +3
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),…
MEMLA: Enhancing Multilingual Knowledge Editing with Neuron-Masked Low-Rank Adaptation
Jiakuan Xie, Pengfei Cao, Yuheng Chen +3
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 knowl…
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
Zhuoran Jin, Pengfei Cao, Chenhao Wang +6
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 m…
Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness
Jiachun Li, Pengfei Cao, Yubo Chen +5
Chain-of-thought (CoT) prompting demonstrates varying performance under different reasoning tasks. Previous work attempts to evaluate it but falls short in providing an in-depth an…
Knowledge Localization: Mission Not Accomplished? Enter Query Localization!
Yuheng Chen, Pengfei Cao, Yubo Chen +2
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…
Continual Few-shot Event Detection via Hierarchical Augmentation Networks
Chenlong Zhang, Pengfei Cao, Yubo Chen +4
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 con…
Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning
Zhitao He, Pengfei Cao, Zhuoran Jin +5
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-resou…
AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation
Zhitao He, Pengfei Cao, Chenhao Wang +7
With the development of deep learning, natural language processing technology has effectively improved the efficiency of various aspects of the traditional judicial industry. Howev…
Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models
Hongbang Yuan, Pengfei Cao, Zhuoran Jin +4
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 hallucinati…
Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
Zhuoran Jin, Pengfei Cao, Hongbang Yuan +6
Recently, retrieval augmentation and tool augmentation have demonstrated a remarkable capability to expand the internal memory boundaries of language models (LMs) by providing exte…
Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models
Zhuoran Jin, Pengfei Cao, Yubo Chen +5
Retrieval-augmented language models (RALMs) have demonstrated significant potential in refining and expanding their internal memory by retrieving evidence from external sources. Ho…
Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning
Jiachun Li, Pengfei Cao, Chenhao Wang +5
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 l…
Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models
Yuheng Chen, Pengfei Cao, Yubo Chen +4
Large language models (LLMs) store extensive factual knowledge, but the underlying mechanisms remain unclear. Previous research suggests that factual knowledge is stored within mul…