Imagen de Portada

Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zeng, Qinglin, Yang, Jing, Wang, Keze
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction
por: Zhang, Jensen, et al.
Publicado: (2025)

Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained Reflection
por: Yang, Zongxian, et al.
Publicado: (2025)

Boosting LLM Reasoning via Spontaneous Self-Correction
por: Zhao, Xutong, et al.
Publicado: (2025)

ORACLE: Optimizing Reasoning Abilities of Large Language Models via Constraint-Led Synthetic Data Elicitation
por: Yang, Zhuojie, et al.
Publicado: (2026)

Fact-Level Confidence Calibration and Self-Correction
por: Yuan, Yige, et al.
Publicado: (2024)

A Scalable Curiosity-Driven Game-Theoretic Framework for Long-Tail Multi-Label Learning in Data Mining
por: Yang, Jing, et al.
Publicado: (2026)

MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction
por: Huang, Yue, et al.
Publicado: (2025)

Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
por: Yan, Hanqi, et al.
Publicado: (2024)

CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation
por: Zeng, Qinglin, et al.
Publicado: (2025)

SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
por: Qin, You, et al.
Publicado: (2026)

Large Language Models as Discounted Bayesian Filters
por: Zhang, Jensen, et al.
Publicado: (2025)

RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability
por: Cai, Kaitong, et al.
Publicado: (2025)

Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning
por: He, Qianxi, et al.
Publicado: (2025)

Failure-Driven Workflow Refinement
por: Zhang, Jusheng, et al.
Publicado: (2025)

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
por: Xu, Tianyang, et al.
Publicado: (2024)

Agent-GSPO: Communication-Efficient Multi-Agent Systems via Group Sequence Policy Optimization
por: Fan, Yijia, et al.
Publicado: (2025)

Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models
por: Li, Loka, et al.
Publicado: (2024)

History-Guided Iterative Visual Reasoning with Self-Correction
por: Yang, Xinglong, et al.
Publicado: (2026)

Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction
por: Zhe, Tao, et al.
Publicado: (2026)

ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control
por: Tang, Zhentao, et al.
Publicado: (2026)

FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research
por: Recchia, Gabriel, et al.
Publicado: (2025)

Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
por: Zhang, Jesen, et al.
Publicado: (2025)

Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
por: Zhang, Xiang, et al.
Publicado: (2025)

MedCritical: Enhancing Medical Reasoning in Small Language Models via Self-Collaborative Correction
por: Su, Xinchun, et al.
Publicado: (2025)

Self-Correcting VLA: Online Action Refinement via Sparse World Imagination
por: Liu, Chenyv, et al.
Publicado: (2026)

HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
por: Tang, Jinzhou, et al.
Publicado: (2025)

Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention
por: Zhang, Yichi, et al.
Publicado: (2025)

AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents
por: Zhang, Zhixing, et al.
Publicado: (2026)

Large Language Models Cannot Self-Correct Reasoning Yet
por: Huang, Jie, et al.
Publicado: (2023)

LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning
por: Ishay, Adam, et al.
Publicado: (2026)

RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks
por: Liu, Ningyuan, et al.
Publicado: (2025)

Guardian: Decoupling Exploration from Safety in Reinforcement Learning
por: Cai, Kaitong, et al.
Publicado: (2025)

Learning Dynamics of VLM Finetuning
por: Zhang, Jusheng, et al.
Publicado: (2025)

Numerical Sensitivity and Robustness: Exploring the Flaws of Mathematical Reasoning in Large Language Models
por: Sun, Zhishen, et al.
Publicado: (2025)

Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
por: Xu, Yuanda, et al.
Publicado: (2026)

Beyond Output Critique: Self-Correction via Task Distillation
por: Rahmani, Hossein A., et al.
Publicado: (2026)

Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification
por: He, Paul, et al.
Publicado: (2026)

Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning
por: Sun, Xinhai
Publicado: (2026)

Decomposing LLM Self-Correction: The Accuracy-Correction Paradox and Error Depth Hypothesis
por: Li, Yin
Publicado: (2025)

Generalized Discrete Diffusion with Self-Correction
por: Wang, Linxuan, et al.
Publicado: (2026)