arXiv · AI· Zirui Ding (Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences), Xinxin Fan (University of Chinese Academy of Sciences, State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences), Hao Yuan (Institute of Computing Technology, Chinese Academy of Sciences, ShanghaiTech University), Shaoye Luo (University of Chinese Academy of Sciences, State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences), Men Niu (Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences), Yunfeng Lu (Beihang University)·· 5 小时前AI 评分26
LLM 失败机制诊断框架 CauTrace 研究
Uncovering Why LLMs Fail: From Internal Mechanisms to Adversarial Reasoning Trajectories
AI 导读
CauTrace 框架通过功能状态、表征传播及时间状态协调三项检查，定位 LLM 在推理过程中的失败根因。在 Qwen 和 LLaMA 系列模型上验证，失败轨迹表现为支持状态更新的 Attention-MLP 一致性较弱且验证活动少于承诺活动。 该发现为深入理解 LLM 安全及推理过程中的失败动态提供了统一诊断视角。
来源：arXiv · AI · arxiv.org