Imagen de Portada

Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohammadi, Hadi, Kozak, Tamas, Giachanou, Anastasia
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models
por: Mohammadi, Hadi, et al.
Publicado: (2025)

Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation
por: Mohammadi, Hadi, et al.
Publicado: (2025)

Explainability in Practice: A Survey of Explainable NLP Across Various Domains
por: Mohammadi, Hadi, et al.
Publicado: (2025)

Explainability-Based Token Replacement on LLM-Generated Text
por: Mohammadi, Hadi, et al.
Publicado: (2025)

Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
por: Jia, Jinghan, et al.
Publicado: (2026)

Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
por: Tutek, Martin, et al.
Publicado: (2025)

Faithful Logical Reasoning via Symbolic Chain-of-Thought
por: Xu, Jundong, et al.
Publicado: (2024)

Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning
por: Ye, Donald, et al.
Publicado: (2026)

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
por: Paul, Debjit, et al.
Publicado: (2024)

On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models
por: Tanneru, Sree Harsha, et al.
Publicado: (2024)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
por: Arcuschin, Iván, et al.
Publicado: (2025)

Scheherazade: Evaluating Chain-of-Thought Math Reasoning in LLMs with Chain-of-Problems
por: Miner, Stephen, et al.
Publicado: (2024)

A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
por: Zhao, Raoyuan, et al.
Publicado: (2025)

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

Improving Stance Detection by Leveraging Measurement Knowledge from Social Sciences: A Case Study of Dutch Political Tweets and Traditional Gender Role Division
por: Fang, Qixiang, et al.
Publicado: (2022)

A Survey on Stereotype Detection in Natural Language Processing
por: Cignarella, Alessandra Teresa, et al.
Publicado: (2025)

It Takes Two: Your GRPO Is Secretly DPO
por: Wu, Yihong, et al.
Publicado: (2025)

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
por: Mittal, Avni, et al.
Publicado: (2026)

Efficient Reasoning for LLMs through Speculative Chain-of-Thought
por: Wang, Jikai, et al.
Publicado: (2025)

Counterfactual Simulation Training for Chain-of-Thought Faithfulness
por: Hase, Peter, et al.
Publicado: (2026)

Demystifying Long Chain-of-Thought Reasoning in LLMs
por: Yeo, Edward, et al.
Publicado: (2025)

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
por: Zhang, Xuan, et al.
Publicado: (2024)

GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought
por: Lv, Weijiang, et al.
Publicado: (2026)

SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs
por: Xu, Yige, et al.
Publicado: (2025)

DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs
por: Cao, Shidong, et al.
Publicado: (2026)

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
por: Zaman, Kerem, et al.
Publicado: (2025)

Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs
por: Ahrend, Patrick, et al.
Publicado: (2026)

ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
por: Zou, Jiaru, et al.
Publicado: (2025)

Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness
por: Li, Jiachun, et al.
Publicado: (2024)

Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity
por: Meek, Austin, et al.
Publicado: (2025)

GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA
por: Wang, Zhichao
Publicado: (2025)

GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients
por: Kazama, Kentaro, et al.
Publicado: (2026)

Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs
por: Yuan, Hongyuan, et al.
Publicado: (2026)

SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models
por: Lv, Weijiang, et al.
Publicado: (2026)

LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data
por: Yang, Cehao, et al.
Publicado: (2025)

Context-DPO: Aligning Language Models for Context-Faithfulness
por: Bi, Baolong, et al.
Publicado: (2024)

Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs
por: Nguyen, Minh-Vuong, et al.
Publicado: (2024)

Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs
por: Cao, Jie, et al.
Publicado: (2026)

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

Chain-of-Thought Reasoning Without Prompting
por: Wang, Xuezhi, et al.
Publicado: (2024)