Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Wenkai, Yang, Fan, Hazarika, Ananya, Mehta, Shaunak A., Onoue, Koichi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs
di: Li, Wenkai, et al.
Pubblicazione: (2026)

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

Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation
di: Jiang, Zhaoyang, et al.
Pubblicazione: (2026)

Markov Chain of Thought for Efficient Mathematical Reasoning
di: Yang, Wen, et al.
Pubblicazione: (2024)

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

Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
di: Dai, Chengwei, et al.
Pubblicazione: (2024)

Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text
di: Agrahari, Shifali, et al.
Pubblicazione: (2025)

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning
di: Shen, Xu, et al.
Pubblicazione: (2025)

Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models
di: Yu, Wenhan, et al.
Pubblicazione: (2025)

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
di: Li, Zeju, et al.
Pubblicazione: (2025)

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
di: Lu, Chengda, et al.
Pubblicazione: (2025)

Streaming Hallucination Detection in Long Chain-of-Thought Reasoning
di: Lu, Haolang, et al.
Pubblicazione: (2026)

How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation
di: Yang, Hao, et al.
Pubblicazione: (2025)

LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
di: Jiang, Zhuoxuan, et al.
Pubblicazione: (2024)

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

Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
di: Wang, Zefeng, et al.
Pubblicazione: (2024)

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning
di: Chen, Qiguang, et al.
Pubblicazione: (2026)

Fractured Chain-of-Thought Reasoning
di: Liao, Baohao, et al.
Pubblicazione: (2025)

Unveiling Confirmation Bias in Chain-of-Thought Reasoning
di: Wan, Yue, et al.
Pubblicazione: (2025)

Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?
di: von Recum, Alexander, et al.
Pubblicazione: (2026)

Diagnosing Pathological Chain-of-Thought in Reasoning Models
di: Liu, Manqing, et al.
Pubblicazione: (2026)

Reasoning Models Struggle to Control their Chains of Thought
di: Yueh-Han, Chen, et al.
Pubblicazione: (2026)

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs
di: Lu, Yu-An, et al.
Pubblicazione: (2026)

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning
di: Jiang, Gangwei, et al.
Pubblicazione: (2025)

CtrlCoT: Dual-Granularity Chain-of-Thought Compression for Controllable Reasoning
di: Fan, Zhenxuan, et al.
Pubblicazione: (2026)

Latent Chain-of-Thought for Visual Reasoning
di: Sun, Guohao, et al.
Pubblicazione: (2025)

ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning
di: Xiong, Xuan, et al.
Pubblicazione: (2026)

Reason from Future: Reverse Thought Chain Enhances LLM Reasoning
di: Xu, Yinlong, et al.
Pubblicazione: (2025)

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning
di: Huang, Chenxi, et al.
Pubblicazione: (2025)

Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
di: Fei, Hao, et al.
Pubblicazione: (2024)

Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
di: Ye, Jiacheng, et al.
Pubblicazione: (2024)

SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
di: Jiang, Fengqing, et al.
Pubblicazione: (2025)

To Reason or Not to: Selective Chain-of-Thought in Medical Question Answering
di: Zhan, Zaifu, et al.
Pubblicazione: (2026)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
di: Chen, Xi, et al.
Pubblicazione: (2025)

Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
di: Yu, Xiangning, et al.
Pubblicazione: (2025)

Watch Your Steps: Observable and Modular Chains of Thought
di: Cohen, Cassandra A., et al.
Pubblicazione: (2024)

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
di: Fan, Shengda, et al.
Pubblicazione: (2026)

Generating Verifiable Chain of Thoughts from Exection-Traces
di: Thakur, Shailja, et al.
Pubblicazione: (2025)

Understanding Reasoning in Chain-of-Thought from the Hopfieldian View
di: Hu, Lijie, et al.
Pubblicazione: (2024)

GRACE: Discriminator-Guided Chain-of-Thought Reasoning
di: Khalifa, Muhammad, et al.
Pubblicazione: (2023)