CauTrace：揭示 LLM 推理失败根源的白盒诊断框架
Uncovering Why LLMs Fail: From Internal Mechanisms to Adversarial Reasoning Trajectories
中科院计算所等团队提出白盒诊断框架 CauTrace，从功能状态、表征传播、时序状态协调与推理轨迹三个维度剖析 LLM 失败成因。在 Qwen 与 LLaMA 系列模型上，失败轨迹表现出支持状态更新时 Attention-MLP 一致性更弱、验证活动相对承诺更少，具体表征特征与时序偏移因架构而异。留出修复与引导实验显示，对齐引导能产生预测方向上的过程指标变化。
Authors:Zirui Ding (1,2), Xinxin Fan (2,3), Hao Yuan (1,4), Shaoye Luo (2,3), Men Niu (1,2), Yunfeng Lu (5) ((1) Institute of Computing Technology, Chinese Academy of Sciences, (2) University of Chinese Academy of Sciences, (3) State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, (4) ShanghaiTech University, (5) Beihang University)
Abstract:Large language models (LLMs) are usually evaluated by final-output correctness or safety, yet an endpoint label does not reveal how a failure develops throughout the reasoning process. We therefore ask whether ordinary reasoning failures and adversarially induced failures can be characterized using the same internal coordinates. Towards this end, we in this paper study a white-box diagnostic framework CauTrace to disclose the root-cause of why LLM fails from three fundamental inspections: Functional States, Propagation of Representation, Temporal-State Coordination and Reasoning Trajectory. First, seven functional states are creatively defined to represent the support and constraint processing in LLMs. Second, the propagation of representation change measures how the changes among the seven states persist across subsequent Transformer blocks. Third, temporal-state coordination and trajectory topology characterize when the commitment and verification occur relative to the support, and how the dominant state sequence evolves over the full inference process. Finally, we evaluate CauTrace on both clean reasoning failures and paired adversarial perturbations. Across Qwen and LLaMA-family models, the failed traces show weaker Attention-MLP agreement on support-state updates and less verification activity relative to commitment, while the exact representation-level signatures and timing shifts vary by architecture. Held-out repair and steering tests demonstrate consistent operational signals that were in line with our claims for certain models and specific settings, with aligned steering producing the predicted directional changes in process measures. Overall, CauTrace provides a unified diagnostic framework for analyzing failure dynamics through changes in support, commitment, and verification, which would shed light on the in-depth research on LLM security.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37369 [cs.AI] |
| (or arXiv:2610.37369v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37369 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zirui Ding [view email]
[v1]
Tue, 27 Oct 2026 15:02:04 UTC (1,719 KB)
来源：arXiv cs.AI · arxiv.org