6 papers
HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning
Yangfan Wang, Tianyang Sun, Chen Tang +3
Lifelong model editing (LME) aims to sequentially rectify outdated or inaccurate knowledge in deployed LLMs while minimizing side effects on unrelated inputs. However, existing app…
Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios
Hui Liu, Bin Zou, Kecheng Chen +3
Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet u…
CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task
Haosi Mo, Xinyu Ma, Xuebo Liu +4
Recent advances in Large Language Models (LLMs) have significantly enhanced their capabilities, highlighting the need for comprehensive evaluation frameworks that extend beyond tas…
MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching
Liang Yue, Yihong Tang, Kehai Chen +2
Instruction fine-tuning is crucial in NLP tasks, enhancing pretrained models' instruction-following capabilities and task-specific performance. However, obtaining high-quality fine…
GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent
Bin Xie, Rui Shao, Gongwei Chen +5
GUI automation faces critical challenges in dynamic environments. MLLMs suffer from two key issues: misinterpreting UI components and outdated knowledge. Traditional fine-tuning me…
The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents
Yihong Tang, Kehai Chen, Xuefeng Bai +4
Large Language Models (LLMs) have made remarkable advances in role-playing dialogue agents, demonstrating their utility in character simulations. However, it remains challenging fo…