6 papers
An Information-Theoretic Framework for Robust Large Language Model Editing
Qizhou Chen, Chengyu Wang, Taolin Zhang +1
Large Language Models (LLMs) have become indispensable tools in science, technology, and society, enabling transformative advances across diverse fields. However, errors or outdate…
QueueEDIT: Structural Self-Correction for Sequential Model Editing in LLMs
Taolin Zhang, Haidong Kang, Dongyang Li +3
Recently, large language models (LLMs) have demonstrated impressive results but still suffer from hallucinations. Model editing has been proposed to correct factual inaccuracies in…
BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering
Taolin Zhang, Dongyang Li, Qizhou Chen +2
Multi-hop question answering (QA) involves finding multiple relevant passages and performing step-by-step reasoning to answer complex questions. Previous works on multi-hop QA empl…
UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models
Qizhou Chen, Dakan Wang, Taolin Zhang +4
Model editing aims to enhance the accuracy and reliability of large language models (LLMs) by efficiently adjusting their internal parameters. Currently, most LLM editing datasets…
Concept Based Continuous Prompts for Interpretable Text Classification
Qian Chen, Dongyang Li, Xiaofeng He
Continuous prompts have become widely adopted for augmenting performance across a wide range of natural language tasks. However, the underlying mechanism of this enhancement remain…
Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
Qizhou Chen, Chengyu Wang, Dakan Wang +3
Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This ta…