Cover Image

Data Shifts Hurt CoT: A Theoretical Study

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yin, Lang, Banerjee, Debangshu, Singh, Gagandeep
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Relational DNN Verification With Cross Executional Bound Refinement
by: Banerjee, Debangshu, et al.
Published: (2024)

Towards Reliable Alignment: Uncertainty-aware RLHF
by: Banerjee, Debangshu, et al.
Published: (2024)

Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs
by: Banerjee, Debangshu, et al.
Published: (2023)

Towards Reliable, Uncertainty-Aware Alignment
by: Banerjee, Debangshu, et al.
Published: (2025)

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
by: Deng, Yuntian, et al.
Published: (2024)

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
by: Sprague, Zayne, et al.
Published: (2024)

Difficult Examples Hurt Unsupervised Contrastive Learning: A Theoretical Perspective
by: Zhang, Yi-Ge, et al.
Published: (2025)

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation
by: Zhang, Ruichen, et al.
Published: (2025)

Support is All You Need for Certified VAE Training
by: Xu, Changming, et al.
Published: (2025)

The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
by: Lan, Yifan, et al.
Published: (2026)

Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning
by: Yao, Xinhao, et al.
Published: (2025)

BEAVER: An Efficient Deterministic LLM Verifier
by: Suresh, Tarun, et al.
Published: (2025)

Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks
by: Liang, Jia, et al.
Published: (2026)

Probabilistic Trust Intervals for Out of Distribution Detection
by: Singh, Gagandeep, et al.
Published: (2021)

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
by: Arnav, Benjamin, et al.
Published: (2025)

To CoT or To Loop? A Formal Comparison Between Chain-of-Thought and Looped Transformers
by: Xu, Kevin, et al.
Published: (2025)

Exploring the Limitations of Mamba in COPY and CoT Reasoning
by: Ren, Ruifeng, et al.
Published: (2024)

The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs
by: Howe, Nikolaus, et al.
Published: (2025)

The Pitfalls of Memorization: When Memorization Hurts Generalization
by: Bayat, Reza, et al.
Published: (2024)

Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization
by: Gu, Yujie, et al.
Published: (2026)

Is continuous CoT better suited for multi-lingual reasoning?
by: Bashir, Ali Hamza, et al.
Published: (2026)

Shorter Thoughts, Same Answers: Difficulty-Scaled Segment-Wise RL for CoT Compression
by: Tian, Ye, et al.
Published: (2026)

Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
by: Wang, Shengjie, et al.
Published: (2026)

RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?
by: Xu, Haotian, et al.
Published: (2025)

CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations
by: Kothapalli, Vignesh, et al.
Published: (2025)

Cross Domain Evaluation of Multimodal Chain-of-Thought Reasoning of different datasets into the Amazon CoT Framework
by: Tiwari, Nitya, et al.
Published: (2025)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
by: Xu, Yinglun, et al.
Published: (2024)

How Likely Do LLMs with CoT Mimic Human Reasoning?
by: Bao, Guangsheng, et al.
Published: (2024)

Meta-CoT: Enhancing Granularity and Generalization in Image Editing
by: Zhang, Shiyi, et al.
Published: (2026)

Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
by: Armandpour, Mohammadreza, et al.
Published: (2026)

PepThink-R1: LLM for Interpretable Cyclic Peptide Optimization with CoT SFT and Reinforcement Learning
by: Wang, Ruheng, et al.
Published: (2025)

To Think or Not to Think: The Hidden Cost of Meta-Training with Excessive CoT Examples
by: Kothapalli, Vignesh, et al.
Published: (2025)

CRANE: Reasoning with constrained LLM generation
by: Banerjee, Debangshu, et al.
Published: (2025)

When Correct Demonstrations Hurt: Rethinking the Role of Exemplars in In-Context Learning
by: Qiu, Chenghao, et al.
Published: (2026)

Certifying Knowledge Comprehension in LLMs
by: Chaudhary, Isha, et al.
Published: (2024)

Formal Synthesis of Certifiably Robust Neural Lyapunov-Barrier Certificates
by: Wang, Chengxiao, et al.
Published: (2026)

LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
by: Ye, Xinwu, et al.
Published: (2026)

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
by: Tong, Chengzhuo, et al.
Published: (2025)

More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
by: Dalal, Gal, et al.
Published: (2026)

On the Expressive Power of Tree-Structured Probabilistic Circuits
by: Yin, Lang, et al.
Published: (2024)