Imagen de Portada

How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Hao, Zhao, Qinghua, Li, Lei, Meng, Lingyi, Yu, Mengda
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Chain-of-Thought in Large Language Models: Decoding, Projection, and Activation
por: Yang, Hao, et al.
Publicado: (2024)

Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations
por: Zheng, Kaiyuan, et al.
Publicado: (2025)

Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering
por: Cox, Kyle, et al.
Publicado: (2026)

HiCoTraj:Zero-Shot Demographic Reasoning via Hierarchical Chain-of-Thought Prompting from Trajectory
por: Xie, Junyi, et al.
Publicado: (2025)

Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer
por: Lu, Wenquan, et al.
Publicado: (2025)

Activation Steering for Chain-of-Thought Compression
por: Azizi, Seyedarmin, et al.
Publicado: (2025)

SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
por: Li, Guanghao, et al.
Publicado: (2025)

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

When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
por: Li, Wenkai, et al.
Publicado: (2026)

Chain-of-Thought Hijacking
por: Zhao, Jianli, et al.
Publicado: (2025)

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

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

Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression
por: Li, Chengzhengxu, et al.
Publicado: (2025)

Learning to Maximize Mutual Information for Chain-of-Thought Distillation
por: Chen, Xin, et al.
Publicado: (2024)

Intention Chain-of-Thought Prompting with Dynamic Routing for Code Generation
por: Li, Shen, et al.
Publicado: (2025)

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

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

Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models
por: Liu, Peijie, et al.
Publicado: (2025)

Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought
por: Yamaguchi, Shin'ya, et al.
Publicado: (2025)

Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors
por: Yang, Hao, et al.
Publicado: (2025)

Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs
por: Xia, Yu, et al.
Publicado: (2024)

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

The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
por: Pengmei, Zihan, et al.
Publicado: (2025)

Chain-of-Thought Predictive Control
por: Jia, Zhiwei, et al.
Publicado: (2023)

Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization
por: Wang, Jiecong, et al.
Publicado: (2026)

Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding
por: Vukovic, Renato, et al.
Publicado: (2024)

Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
por: Aravindan, Ashwath Vaithinathan, et al.
Publicado: (2026)

Rethinking Chain-of-Thought from the Perspective of Self-Training
por: Wu, Zongqian, et al.
Publicado: (2024)

Understanding Chain-of-Thought in LLMs through Information Theory
por: Ton, Jean-Francois, et al.
Publicado: (2024)

Chain Of Thought Compression: A Theoretical Analysis
por: Li, Juncai, et al.
Publicado: (2026)

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

COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models
por: Fayyazi, Arya, et al.
Publicado: (2026)

Expediting and Elevating Large Language Model Reasoning via Hidden Chain-of-Thought Decoding
por: Liu, Tianqiao, et al.
Publicado: (2024)

Call-Chain-Aware LLM-Based Test Generation for Java Projects
por: Wang, Guancheng, et al.
Publicado: (2026)

Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
por: Yang, Kia-Jüng, et al.
Publicado: (2026)

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

Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
por: Wu, Yuan, et al.
Publicado: (2026)

Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?
por: Young, Richard J.
Publicado: (2026)

EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation
por: Li, Zihang, et al.
Publicado: (2026)

Scalable Chain of Thoughts via Elastic Reasoning
por: Xu, Yuhui, et al.
Publicado: (2025)