Imagen de Portada

The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zheng, Tianshi, Chen, Yixiang, Li, Chengxi, Li, Chunyang, Zong, Qing, Shi, Haochen, Xu, Baixuan, Song, Yangqiu, Wong, Ginny Y., See, Simon
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning
por: Zheng, Tianshi, et al.
Publicado: (2025)

CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?
por: Zong, Qing, et al.
Publicado: (2025)

Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
por: Xu, Baixuan, et al.
Publicado: (2025)

INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling
por: Shi, Haochen, et al.
Publicado: (2025)

NAACL: Noise-AwAre Verbal Confidence Calibration for Robust LLMs in RAG Systems
por: Liu, Jiayu, et al.
Publicado: (2026)

Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations
por: Li, Chunyang, et al.
Publicado: (2025)

MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
por: Ren, Xiyu, et al.
Publicado: (2026)

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation
por: Wang, Zhaowei, et al.
Publicado: (2024)

ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty
por: Zong, Qing, et al.
Publicado: (2024)

DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
por: Mo, Yunxiang, et al.
Publicado: (2025)

$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
por: Wang, Zihao, et al.
Publicado: (2026)

Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents
por: Fan, Wei, et al.
Publicado: (2025)

Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
por: Shao, Hao, et al.
Publicado: (2024)

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

Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty
por: Wang, Rui, et al.
Publicado: (2025)

NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
por: Zheng, Tianshi, et al.
Publicado: (2025)

CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning
por: Fang, Yuanheng, et al.
Publicado: (2025)

CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-Thought
por: Zhang, Bowen, et al.
Publicado: (2023)

Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
por: Fan, Wei, et al.
Publicado: (2026)

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

Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering
por: Fan, Lin, et al.
Publicado: (2026)

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
por: Xu, Baixuan, et al.
Publicado: (2025)

Persona Knowledge-Aligned Prompt Tuning Method for Online Debate
por: Chan, Chunkit, et al.
Publicado: (2024)

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

AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning
por: Li, Xiping, et al.
Publicado: (2025)

CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
por: Zhao, Qingqing, et al.
Publicado: (2025)

EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understanding
por: Lau, Ching Ming Samuel, et al.
Publicado: (2024)

CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning
por: Feng, Kehua, et al.
Publicado: (2025)

KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning
por: Mondal, Debjyoti, et al.
Publicado: (2024)

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

ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning
por: Liao, Jiaqi, et al.
Publicado: (2025)

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
por: Chen, Xinyan, et al.
Publicado: (2025)

Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models
por: Li, Aaron Branson Cigres, 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)

EFT-CoT: A Multi-Agent Chain-of-Thought Framework for Emotion-Focused Therapy
por: Du, Lanqing, et al.
Publicado: (2026)

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
por: Wang, Zhaowei, et al.
Publicado: (2025)

Co-CoT: A Prompt-Based Framework for Collaborative Chain-of-Thought Reasoning
por: Yoo, Seunghyun
Publicado: (2025)

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

C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving
por: Tian, Kefei, et al.
Publicado: (2026)

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