5 papers
A Few Neurons Reveal When LLMs Misuse Tools: Sparse Detection and Selective Steering for Reliable Tool Use
Yutong Ke, Ming Yin, Chongwen Zhao +1
Agentic LLMs exhibit three consequential tool-use failures: invalid arguments (validity), unnecessary calls (over-calling), and omitted calls when tools are needed (missing). We fi…
NumCoKE: Ordinal-Aware Numerical Reasoning over Knowledge Graphs with Mixture-of-Experts and Contrastive Learning
Ming Yin, Zongsheng Cao, Qiqing Xia +2
Knowledge graphs (KGs) serve as a vital backbone for a wide range of AI applications, including natural language understanding and recommendation. A promising yet underexplored dir…
Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
Shaokun Zhang, Ming Yin, Jieyu Zhang +8
Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored a…
Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
Yudong Liu, Jingwei Sun, Yueqian Lin +6
Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to red…
Investigating Creativity in Humans and Generative AI Through Circles Exercises
Runlin Duan, Shao-Kang Hsia, Yuzhao Chen +3
Generative AI (GenAI) is transforming the creativity process. However, as presented in this paper, GenAI encounters "narrow creativity" barriers. We observe that both humans and Ge…