Imagen de Portada

Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Chen, Wu, Yuhao, Wang, Lei, Zhang, Wenxuan, Shen, Fumin
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning
por: Lyu, Tianwen, et al.
Publicado: (2025)

Evaluating LLM Reasoning Beyond Correctness and CoT
por: Abbasloo, Soheil
Publicado: (2025)

The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics
por: Bachmann, Gregor, et al.
Publicado: (2026)

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

Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation
por: Luo, Yijia, et al.
Publicado: (2025)

Decoding Answers Before Chain-of-Thought: Evidence from Pre-CoT Probes and Activation Steering
por: Cox, Kyle, et al.
Publicado: (2026)

CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation
por: Huang, Dong, et al.
Publicado: (2023)

Efficient Long CoT Reasoning in Small Language Models
por: Wang, Zhaoyang, et al.
Publicado: (2025)

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

KG-Augmented Executable CoT for Mathematical Coding
por: Chen, Xingyu, et al.
Publicado: (2025)

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

CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
por: Chen, Shuxu, et al.
Publicado: (2026)

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

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation
por: Li, Haodong, et al.
Publicado: (2026)

GTR-CoT: Graph Traversal as Visual Chain of Thought for Molecular Structure Recognition
por: Wang, Jingchao, et al.
Publicado: (2025)

Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning
por: Hong, Jialiang, et al.
Publicado: (2025)

Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
por: Yang, Cehao, et al.
Publicado: (2025)

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
por: Yun, Taewon, et al.
Publicado: (2026)

Chain of Thoughtlessness? An Analysis of CoT in Planning
por: Stechly, Kaya, et al.
Publicado: (2024)

CoT-Guard: Small Models for Strong Monitoring
por: Diwan, Nirav, et al.
Publicado: (2026)

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction
por: Zhang, Chen, et al.
Publicado: (2026)

Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA
por: Schumann, Raphael, et al.
Publicado: (2025)

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

VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing
por: Shi, Haoyuan, et al.
Publicado: (2026)

Bridging Efficiency and Transparency: Explainable CoT Compression in Multimodal Large Reasoning Models
por: Wang, Yizhi, et al.
Publicado: (2026)

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
por: Luo, Haotian, et al.
Publicado: (2025)

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning
por: Yao, Jian, et al.
Publicado: (2026)

CoT-Driven Framework for Short Text Classification: Enhancing and Transferring Capabilities from Large to Smaller Model
por: Wu, Hui, et al.
Publicado: (2024)

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

CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization
por: Bi, Ziqian, et al.
Publicado: (2025)

TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories
por: Nian, Junjie, et al.
Publicado: (2026)

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

Chain-of-Tools: Utilizing Massive Unseen Tools in the CoT Reasoning of Frozen Language Models
por: Wu, Mengsong, et al.
Publicado: (2025)

SIM-CoT: Supervised Implicit Chain-of-Thought
por: Wei, Xilin, et al.
Publicado: (2025)

Hybrid Distillation with CoT Guidance for Edge-Drone Control Code Generation
por: Feng, Yizhan, et al.
Publicado: (2026)

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
por: Li, Jianan, et al.
Publicado: (2026)

D-SCoRE: Document-Centric Segmentation and CoT Reasoning with Structured Export for QA-CoT Data Generation
por: Zhou, Weibo, et al.
Publicado: (2025)

Multiplicative-Additive Constrained Models:Toward Joint Visualization of Interactive and Independent Effects
por: Wang, Fumin
Publicado: (2025)

CoT-VLM4Tar: Chain-of-Thought Guided Vision-Language Models for Traffic Anomaly Resolution
por: Ren, Tianchi, et al.
Publicado: (2025)

CoT-Valve: Length-Compressible Chain-of-Thought Tuning
por: Ma, Xinyin, et al.
Publicado: (2025)