23 papers
REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning
Zhensheng Jin, Xin Dai, Zhenghao Liu +5
Large Language Models (LLMs) increasingly leverage long-form reasoning to solve complex tasks, yet their reasoning processes can deviate from the provided context when evidence is…
SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation
Ruochang Li, Pengcheng Huang, Zhenghao Liu +5
Retrieval-augmented generation (RAG) enhances LLMs by incorporating external knowledge to support response generation. However, conflicts between retrieved context and parametric k…
Memory Shot for Long-Term Dialogue
Chunyi Peng, Haidong Xin, Xuanshuo Sheng +7
Large Language Models (LLMs) have demonstrated strong capabilities in general conversation, instruction following, and complex reasoning. However, in long-term dialogue settings, t…
UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents
Yifan Ji, Zhipeng Xu, Zhenghao Liu +7
Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information req…
Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling
Shuliang Liu, Zhipeng Xu, Zhenghao Liu +6
Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach plays a vital role in aligning LL…
MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization
Haidong Xin, Xinze Li, Zhenghao Liu +6
Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. How…