Copertina

Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zeng, Qinglin, Yang, Jing, Wang, Keze
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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

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

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

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

Failure-Driven Workflow Refinement
di: Zhang, Jusheng, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Learning Dynamics of VLM Finetuning
di: Zhang, Jusheng, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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