2 citations · 15 across the 40 of their papers we have counts for
10 papers · 1 filter
Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory
Derong Xu, Shuochen Liu, Pengfei Luo +8
Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving preferences over long interacti…
MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning
Yimin Deng, Zhenxi Lin, Yejing Wang +9
Diagnostic prediction and clinical reasoning are critical tasks in healthcare applications. While Large Language Models (LLMs) have shown strong capabilities in commonsense reasoni…
MTA: A Merge-then-Adapt Framework for Personalized Large Language Model
Xiaopeng Li, Yuanjin Zheng, Wanyu Wang +6
Personalized Large Language Models (PLLMs) aim to align model outputs with individual user preferences, a crucial capability for user-centric applications. However, the prevalent a…
RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models
Dayan Pan, Jingyuan Wang, Yilong Zhou +3
Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged…
Learning a Single Token to Replace Long System Prompts in LLMs
Jiancheng Dong, Pengyue Jia, Jingyu Peng +7
Long system prompts are widely used to steer Large Language Models (LLMs), but repeatedly processing them at inference time is inefficient and consumes valuable context budget. Thi…
From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
Derong Xu, Yi Wen, Pengyue Jia +8
Large Language Models (LLMs) have recently been widely adopted in conversational agents. However, the increasingly long interactions between users and agents accumulate extensive d…
Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation
Derong Xu, Pengyue Jia, Xiaopeng Li +9
Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks. Graph…
Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression
Jingyu Peng, Maolin Wang, Nan Wang +7
Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to jailbreak attacks. We hypothesize that…
TAPO: Task-Referenced Adaptation for Prompt Optimization
Wenxin Luo, Weirui Wang, Xiaopeng Li +3
Prompt engineering can significantly improve the performance of large language models (LLMs), with automated prompt optimization (APO) gaining significant attention due to the time…
Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation
Pengyue Jia, Derong Xu, Xiaopeng Li +9
The reranker and generator are two critical components in the Retrieval-Augmented Generation (i.e., RAG) pipeline, responsible for ranking relevant documents and generating respons…