Image de couverture de livre

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Puerto, Haritz, Chubakov, Tilek, Zhu, Xiaodan, Madabushi, Harish Tayyar, Gurevych, Iryna
Format:	Preprint
Publié:	2024
Sujets:	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

The Inherent Limits of Pretrained LLMs: The Unexpected Convergence of Instruction Tuning and In-Context Learning Capabilities
par: Bigoulaeva, Irina, et autres
Publié: (2025)

Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs
par: Puerto, Haritz, et autres
Publié: (2024)

Evaluating CxG Generalisation in LLMs via Construction-Based NLI Fine Tuning
par: Mackintosh, Tom, et autres
Publié: (2025)

FS-RAG: A Frame Semantics Based Approach for Improved Factual Accuracy in Large Language Models
par: Madabushi, Harish Tayyar
Publié: (2024)

Are Emergent Abilities in Large Language Models just In-Context Learning?
par: Lu, Sheng, et autres
Publié: (2023)

Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
par: Niu, Jingcheng, et autres
Publié: (2025)

Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces
par: Imperial, Joseph Marvin, et autres
Publié: (2025)

Dancing with Deer: A Constructional Perspective on MWEs in the Era of LLMs
par: Bonial, Claire, et autres
Publié: (2025)

Neither Stochastic Parroting nor AGI: LLMs Solve Tasks through Context-Directed Extrapolation from Training Data Priors
par: Madabushi, Harish Tayyar, et autres
Publié: (2025)

SpeciaLex: A Benchmark for In-Context Specialized Lexicon Learning
par: Imperial, Joseph Marvin, et autres
Publié: (2024)

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves
par: Puerto, Haritz, et autres
Publié: (2026)

Safer Policy Compliance with Dynamic Epistemic Fallback
par: Imperial, Joseph Marvin, et autres
Publié: (2026)

Pre-Trained Language Models Represent Some Geographic Populations Better Than Others
par: Dunn, Jonathan, et autres
Publié: (2024)

DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs
par: Fang, Haishuo, et autres
Publié: (2024)

Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation
par: Imperial, Joseph Marvin, et autres
Publié: (2024)

Robust Utility-Preserving Text Anonymization Based on Large Language Models
par: Yang, Tianyu, et autres
Publié: (2024)

Code-Mixed Probes Show How Pre-Trained Models Generalise On Code-Switched Text
par: De Leon, Frances A. Laureano, et autres
Publié: (2024)

Evaluating Large Language Models on Multiword Expressions in Multilingual and Code-Switched Contexts
par: De Leon, Frances Laureano, et autres
Publié: (2025)

Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance
par: Imperial, Joseph Marvin, et autres
Publié: (2025)

Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings
par: Liu, Chen Cecilia, et autres
Publié: (2023)

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models
par: Rizvi, Md Imbesat Hassan, et autres
Publié: (2024)

Preemptive Detection and Correction of Misaligned Actions in LLM Agents
par: Fang, Haishuo, et autres
Publié: (2024)

Adapting Whisper for Regional Dialects: Enhancing Public Services for Vulnerable Populations in the United Kingdom
par: Torgbi, Melissa, et autres
Publié: (2025)

Word Boundary Information Isn't Useful for Encoder Language Models
par: Gow-Smith, Edward, et autres
Publié: (2024)

Automatic Reviewers Fail to Detect Faulty Reasoning in Research Papers: A New Counterfactual Evaluation Framework
par: Dycke, Nils, et autres
Publié: (2025)

CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning
par: Feng, Kehua, et autres
Publié: (2025)

SciCoQA: Quality Assurance for Scientific Paper--Code Alignment
par: Baumgärtner, Tim, et autres
Publié: (2026)

CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
par: Tong, Zhao, et autres
Publié: (2026)

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
par: Du, Yanrui, et autres
Publié: (2026)

SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling
par: Rizvi, Md Imbesat Hassan, et autres
Publié: (2025)

CoT-Valve: Length-Compressible Chain-of-Thought Tuning
par: Ma, Xinyin, et autres
Publié: (2025)

P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMs
par: Jang, Dongjun, et autres
Publié: (2025)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
par: Li, Li, et autres
Publié: (2025)

Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs
par: Le, Chenqian, et autres
Publié: (2025)

How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study
par: Waldis, Andreas, et autres
Publié: (2023)

Beyond Memorization: Assessing Semantic Generalization in Large Language Models Using Phrasal Constructions
par: Scivetti, Wesley, et autres
Publié: (2025)

Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
par: Kopiczko, Dawid J., et autres
Publié: (2026)

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning
par: Mondal, Debjyoti, et autres
Publié: (2024)

Like a Good Nearest Neighbor: Practical Content Moderation and Text Classification
par: Bates, Luke, et autres
Publié: (2023)

Citation Failure: Definition, Analysis and Efficient Mitigation
par: Buchmann, Jan, et autres
Publié: (2025)