Image de couverture de livre

Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Ru, Huang, Wei, Song, Selena, Zhang, Haoyu, Niu, Qian, Iwasawa, Yusuke, Matsuo, Yutaka, Guo, Jiaxian
Format:	Preprint
Publié:	2025
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

Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection
par: Yang, Bo, et autres
Publié: (2025)

Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
par: Wang, Ru, et autres
Publié: (2025)

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
par: Zhang, Haoyu, et autres
Publié: (2025)

Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
par: Gambardella, Andrew, et autres
Publié: (2024)

Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar
par: Gambardella, Andrew, et autres
Publié: (2025)

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
par: Minegishi, Gouki, et autres
Publié: (2025)

On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
par: Kojima, Takeshi, et autres
Publié: (2024)

Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise
par: Harada, Keno, et autres
Publié: (2025)

$\infty$-MoE: Generalizing Mixture of Experts to Infinite Experts
par: Takashiro, Shota, et autres
Publié: (2026)

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
par: Minegishi, Gouki, et autres
Publié: (2025)

Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models
par: Cao, Qi, et autres
Publié: (2026)

Dynamic Injection of Entity Knowledge into Dense Retrievers
par: Yamada, Ikuya, et autres
Publié: (2025)

Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning
par: Takashiro, Shota, et autres
Publié: (2024)

Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?
par: Uchiyama, Fumiya, et autres
Publié: (2024)

ColorizeDiffusion v2: Enhancing Reference-based Sketch Colorization Through Separating Utilities
par: Yan, Dingkun, et autres
Publié: (2025)

Towards High-resolution and Disentangled Reference-based Sketch Colorization
par: Yan, Dingkun, et autres
Publié: (2026)

Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
par: Guo, Jiaxian, et autres
Publié: (2023)

JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese Large Language Models
par: Liu, Junyu, et autres
Publié: (2026)

Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning
par: Huang, Jerry, et autres
Publié: (2026)

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
par: Jin, Senjie, et autres
Publié: (2025)

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
par: Minegishi, Gouki, et autres
Publié: (2023)

Enhancing Reference-based Sketch Colorization via Separating Reference Representations
par: Yan, Dingkun, et autres
Publié: (2025)

Image Referenced Sketch Colorization Based on Animation Creation Workflow
par: Yan, Dingkun, et autres
Publié: (2025)

When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following
par: Harada, Keno, et autres
Publié: (2025)

Through the Valley: Path to Effective Long CoT Training for Small Language Models
par: Luo, Renjie, et autres
Publié: (2025)

From Chains to Graphs: Self-Structured Reasoning for General-Domain LLMs
par: Chen, Yingjian, et autres
Publié: (2026)

ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making
par: Watanabe, Yusuke, et autres
Publié: (2026)

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
par: Deng, Yuntian, et autres
Publié: (2024)

Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
par: Furuta, Hiroki, et autres
Publié: (2024)

Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Training
par: Odonchimed, Sodtavilan, et autres
Publié: (2025)

Generating Effective CoT Traces for Mitigating Causal Hallucination
par: Zhao, Yiheng, et autres
Publié: (2026)

Beyond Isolated Capabilities: Bridging Long CoT Reasoning and Long-Context Understanding
par: Wang, Yifei
Publié: (2025)

D-SCoRE: Document-Centric Segmentation and CoT Reasoning with Structured Export for QA-CoT Data Generation
par: Zhou, Weibo, et autres
Publié: (2025)

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning
par: Li, Ang, et autres
Publié: (2025)

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
par: Yan, Shaotian, et autres
Publié: (2026)

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
par: Sprague, Zayne, et autres
Publié: (2024)

Efficient Long CoT Reasoning in Small Language Models
par: Wang, Zhaoyang, et autres
Publié: (2025)

Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models
par: Gu, Xiaojie, et autres
Publié: (2026)

QuadNorm: Resolution-Robust Normalization for Neural Operators
par: Kim, Bum Jun, et autres
Publié: (2026)

Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models
par: Kim, Bum Jun, et autres
Publié: (2025)