Image de couverture de livre

When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Wenkai, Yang, Fan, Hazarika, Ananya, Mehta, Shaunak A., Onoue, Koichi
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs
par: Li, Wenkai, et autres
Publié: (2026)

Can We Trust AI Explanations? Evidence of Systematic Underreporting in Chain-of-Thought Reasoning
par: Mehta, Deep Pankajbhai
Publié: (2025)

Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation
par: Jiang, Zhaoyang, et autres
Publié: (2026)

Markov Chain of Thought for Efficient Mathematical Reasoning
par: Yang, Wen, et autres
Publié: (2024)

User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios
par: Wu, Xiaoyuan, et autres
Publié: (2025)

Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
par: Dai, Chengwei, et autres
Publié: (2024)

Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text
par: Agrahari, Shifali, et autres
Publié: (2025)

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning
par: Shen, Xu, et autres
Publié: (2025)

Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models
par: Yu, Wenhan, et autres
Publié: (2025)

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
par: Li, Zeju, et autres
Publié: (2025)

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
par: Lu, Chengda, et autres
Publié: (2025)

Streaming Hallucination Detection in Long Chain-of-Thought Reasoning
par: Lu, Haolang, et autres
Publié: (2026)

How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation
par: Yang, Hao, et autres
Publié: (2025)

LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
par: Jiang, Zhuoxuan, et autres
Publié: (2024)

LLM Reasoning Is Latent, Not the Chain of Thought
par: Wang, Wenshuo
Publié: (2026)

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
par: Wang, Zefeng, et autres
Publié: (2024)

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning
par: Chen, Qiguang, et autres
Publié: (2026)

Fractured Chain-of-Thought Reasoning
par: Liao, Baohao, et autres
Publié: (2025)

Unveiling Confirmation Bias in Chain-of-Thought Reasoning
par: Wan, Yue, et autres
Publié: (2025)

Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?
par: von Recum, Alexander, et autres
Publié: (2026)

Diagnosing Pathological Chain-of-Thought in Reasoning Models
par: Liu, Manqing, et autres
Publié: (2026)

Reasoning Models Struggle to Control their Chains of Thought
par: Yueh-Han, Chen, et autres
Publié: (2026)

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
par: Lu, Yu-An, et autres
Publié: (2026)

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning
par: Jiang, Gangwei, et autres
Publié: (2025)

CtrlCoT: Dual-Granularity Chain-of-Thought Compression for Controllable Reasoning
par: Fan, Zhenxuan, et autres
Publié: (2026)

Latent Chain-of-Thought for Visual Reasoning
par: Sun, Guohao, et autres
Publié: (2025)

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
par: Xiong, Xuan, et autres
Publié: (2026)

Reason from Future: Reverse Thought Chain Enhances LLM Reasoning
par: Xu, Yinlong, et autres
Publié: (2025)

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
par: Huang, Chenxi, et autres
Publié: (2025)

Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
par: Fei, Hao, et autres
Publié: (2024)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
par: Ye, Jiacheng, et autres
Publié: (2024)

SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
par: Jiang, Fengqing, et autres
Publié: (2025)

To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering
par: Zhan, Zaifu, et autres
Publié: (2026)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
par: Chen, Xi, et autres
Publié: (2025)

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
par: Yu, Xiangning, et autres
Publié: (2025)

Watch Your Steps: Observable and Modular Chains of Thought
par: Cohen, Cassandra A., et autres
Publié: (2024)

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
par: Fan, Shengda, et autres
Publié: (2026)

Generating Verifiable Chain of Thoughts from Exection-Traces
par: Thakur, Shailja, et autres
Publié: (2025)

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View
par: Hu, Lijie, et autres
Publié: (2024)

GRACE: Discriminator-Guided Chain-of-Thought Reasoning
par: Khalifa, Muhammad, et autres
Publié: (2023)