Image de couverture de livre

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jia, Jinghan, Benton, Joe, Easley, Eric
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
par: Arcuschin, Iván, et autres
Publié: (2025)

Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
par: Meek, Austin, et autres
Publié: (2025)

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
par: Zaman, Kerem, et autres
Publié: (2025)

Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation
par: Young, Richard J.
Publié: (2026)

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
par: Sun, Jingyi, et autres
Publié: (2026)

Mapping Faithful Reasoning in Language Models
par: Li, Jiazheng, et autres
Publié: (2025)

Multilingual Self-Taught Faithfulness Evaluators
par: Alfano, Carlo, et autres
Publié: (2025)

MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs
par: Liu, Gabrielle Kaili-May, et autres
Publié: (2025)

Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs
par: Mohammadi, Hadi, et autres
Publié: (2025)

Counterfactual Simulation Training for Chain-of-Thought Faithfulness
par: Hase, Peter, et autres
Publié: (2026)

Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning
par: Ye, Donald, et autres
Publié: (2026)

Faithful Logical Reasoning via Symbolic Chain-of-Thought
par: Xu, Jundong, et autres
Publié: (2024)

Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
par: Tutek, Martin, et autres
Publié: (2025)

FaithLM: Towards Faithful Explanations for Large Language Models
par: Chuang, Yu-Neng, et autres
Publié: (2024)

RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
par: Yu, Zichun, et autres
Publié: (2025)

Faithfulness Evaluation for Decoder-only LLM Attributions with Controlled Retained Information
par: Huang, Xin, et autres
Publié: (2026)

FLARE: Faithful Logic-Aided Reasoning and Exploration
par: Arakelyan, Erik, et autres
Publié: (2024)

Are LLM Decisions Faithful to Verbal Confidence?
par: Wang, Jiawei, et autres
Publié: (2026)

Faithfulness Measurable Masked Language Models
par: Madsen, Andreas, et autres
Publié: (2023)

Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict
par: Venkata, Pruthvinath Jeripity
Publié: (2026)

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
par: Paul, Debjit, et autres
Publié: (2024)

On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models
par: Tanneru, Sree Harsha, et autres
Publié: (2024)

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
par: Mittal, Avni, et autres
Publié: (2026)

A Causal Lens for Evaluating Faithfulness Metrics
par: Zaman, Kerem, et autres
Publié: (2025)

Faithful and Robust Local Interpretability for Textual Predictions
par: Lopardo, Gianluigi, et autres
Publié: (2023)

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
par: Cho, Seonglae, et autres
Publié: (2025)

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

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
par: Hanna, Michael, et autres
Publié: (2024)

FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
par: Ming, Yifei, et autres
Publié: (2024)

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
par: Zhang, Xuan, et autres
Publié: (2024)

CRAFT: Calibrated Reasoning with Answer-Faithful Traces via Reinforcement Learning for Multi-Hop Question Answering
par: Liu, Yu, et autres
Publié: (2026)

GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
par: Lv, Weijiang, et autres
Publié: (2026)

Transformer Circuit Faithfulness Metrics are not Robust
par: Miller, Joseph, et autres
Publié: (2024)

Demystifying Long Chain-of-Thought Reasoning in LLMs
par: Yeo, Edward, et autres
Publié: (2025)

Understanding Hidden Computations in Chain-of-Thought Reasoning
par: Bharadwaj, Aryasomayajula Ram
Publié: (2024)

A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
par: Zhao, Raoyuan, et autres
Publié: (2025)

Constraint-Rectified Training for Efficient Chain-of-Thought
par: Wu, Qinhang, et autres
Publié: (2026)

New Faithfulness-Centric Interpretability Paradigms for Natural Language Processing
par: Madsen, Andreas
Publié: (2024)

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

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
par: Gu, Yu, et autres
Publié: (2026)