Buchumschlag

Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Cheng, Xinyuan, Chen, Beiduo, Mondorf, Philipp, Plank, Barbara
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Liar, Liar, Logical Mire: A Benchmark for Suppositional Reasoning in Large Language Models
von: Mondorf, Philipp, et al.
Veröffentlicht: (2024)

Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning
von: Mondorf, Philipp, et al.
Veröffentlicht: (2024)

Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
von: Mondorf, Philipp, et al.
Veröffentlicht: (2024)

Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variation
von: Chen, Beiduo, et al.
Veröffentlicht: (2025)

Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective
von: Chen, Beiduo, et al.
Veröffentlicht: (2026)

LogicSkills: A Structured Benchmark for Formal Reasoning in Large Language Models
von: Rabern, Brian, et al.
Veröffentlicht: (2026)

If Probable, Then Acceptable? Understanding Conditional Acceptability Judgments in Large Language Models
von: Orth, Jasmin, et al.
Veröffentlicht: (2025)

Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discrimination
von: Chen, Qiqi, et al.
Veröffentlicht: (2024)

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
von: Mondorf, Philipp, et al.
Veröffentlicht: (2024)

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It
von: Bertolazzi, Leonardo, et al.
Veröffentlicht: (2025)

Reason to Rote: Rethinking Memorization in Reasoning
von: Du, Yupei, et al.
Veröffentlicht: (2025)

A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI
von: Chen, Beiduo, et al.
Veröffentlicht: (2024)

MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMs
von: Zhao, Raoyuan, et al.
Veröffentlicht: (2025)

Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection
von: Muscato, Benedetta, et al.
Veröffentlicht: (2026)

Tracing Uncertainty in Language Model "Reasoning"
von: Grünefeld, Nils, et al.
Veröffentlicht: (2026)

Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study
von: Mu, Yongyu, et al.
Veröffentlicht: (2025)

Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization
von: Chen, Beiduo, et al.
Veröffentlicht: (2026)

LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference
von: Hong, Pingjun, et al.
Veröffentlicht: (2025)

"Seeing the Big through the Small": Can LLMs Approximate Human Judgment Distributions on NLI from a Few Explanations?
von: Chen, Beiduo, et al.
Veröffentlicht: (2024)

Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations
von: Hong, Pingjun, et al.
Veröffentlicht: (2025)

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

Long Chain-of-Thought Reasoning Across Languages
von: Barua, Josh, et al.
Veröffentlicht: (2025)

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

Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
von: Zbeeb, Mohammad, et al.
Veröffentlicht: (2025)

Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models
von: Yao, Yao, et al.
Veröffentlicht: (2023)

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
von: Cheng, Jeffrey, et al.
Veröffentlicht: (2024)

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
von: Sun, Renliang, et al.
Veröffentlicht: (2025)

Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision
von: Qin, Luozheng, et al.
Veröffentlicht: (2025)

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning
von: Lin, Honglin, et al.
Veröffentlicht: (2025)

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

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

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought
von: Xiang, Violet, et al.
Veröffentlicht: (2025)

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

Efficient Reasoning via Chain of Unconscious Thought
von: Gong, Ruihan, et al.
Veröffentlicht: (2025)

Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
von: Chen, Xinghao, et al.
Veröffentlicht: (2025)

From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification
von: Xu, Shanshan, et al.
Veröffentlicht: (2023)

Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought
von: Son, Guijin, et al.
Veröffentlicht: (2025)

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

On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
von: Nowak, Franz, et al.
Veröffentlicht: (2024)

Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
von: Chen, Qiguang, et al.
Veröffentlicht: (2024)