Copertina

Decomposing LLM Self-Correction: The Accuracy-Correction Paradox and Error Depth Hypothesis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Li, Yin
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

Localizing and Correcting Errors for LLM-based Planners
di: Kumar, Aditya, et al.
Pubblicazione: (2026)

SCANet: Correcting LEGO Assembly Errors with Self-Correct Assembly Network
di: Wan, Yuxuan, et al.
Pubblicazione: (2024)

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
di: Ferraz, Thomas Palmeira, et al.
Pubblicazione: (2024)

Game-Oriented ASR Error Correction via RAG-Enhanced LLM
di: Jiang, Yan, et al.
Pubblicazione: (2025)

Harnessing Rule-Based Reinforcement Learning for Enhanced Grammatical Error Correction
di: Li, Yilin, et al.
Pubblicazione: (2025)

CEC-Zero: Chinese Error Correction Solution Based on LLM
di: Zhang, Sophie, et al.
Pubblicazione: (2025)

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

Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales
di: Li, Tang, et al.
Pubblicazione: (2024)

LLMCL-GEC: Advancing Grammatical Error Correction with LLM-Driven Curriculum Learning
di: Fang, Tao, et al.
Pubblicazione: (2024)

When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
di: Sahoo, Subramanyam, et al.
Pubblicazione: (2026)

Synthetic Error Injection Fails to Elicit Self-Correction In Language Models
di: Wu, David X., et al.
Pubblicazione: (2025)

Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction
di: Ye, Jingheng, et al.
Pubblicazione: (2025)

Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs
di: Liu, Aofan, et al.
Pubblicazione: (2026)

Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation
di: Zheng, Lulu, et al.
Pubblicazione: (2026)

A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation
di: Cao, Cong, et al.
Pubblicazione: (2026)

Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection
di: Park, Taehee, et al.
Pubblicazione: (2025)

DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language Models
di: Xie, Jinxiang, et al.
Pubblicazione: (2024)

Pseudorandom Error-Correcting Codes
di: Christ, Miranda, et al.
Pubblicazione: (2024)

Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction
di: Zeng, Qinglin, et al.
Pubblicazione: (2025)

Semantic Error Correction and Decoding for Short Block Codes
di: Hao, Jiafu, et al.
Pubblicazione: (2026)

On the Error-Correcting Effects of Stochasticity in Discrete Diffusion
di: Yuan, William, et al.
Pubblicazione: (2026)

Learning Linear Block Error Correction Codes
di: Choukroun, Yoni, et al.
Pubblicazione: (2024)

GPT-3.5 for Grammatical Error Correction
di: Katinskaia, Anisia, et al.
Pubblicazione: (2024)

Error Detection and Correction for Interpretable Mathematics in Large Language Models
di: Yang, Yijin, et al.
Pubblicazione: (2025)

Loss-Aware Curriculum Learning for Chinese Grammatical Error Correction
di: Zhang, Ding, et al.
Pubblicazione: (2024)

ChatLang-8: An LLM-Based Synthetic Data Generation Framework for Grammatical Error Correction
di: Park, Jeiyoon, et al.
Pubblicazione: (2024)

CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving
di: Guo, Yihong, et al.
Pubblicazione: (2026)

Learning to Decode in Parallel: Self-Coordinating Neural Network for Real-Time Quantum Error Correction
di: Zhang, Kai, et al.
Pubblicazione: (2026)

Accelerating Error Correction Code Transformers
di: Levy, Matan, et al.
Pubblicazione: (2024)

Rethink the Role of Neural Decoders in Quantum Error Correction
di: Yan, Ge, et al.
Pubblicazione: (2026)

Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLM
di: Prakash, Jeena, et al.
Pubblicazione: (2025)

ToolCritic: Detecting and Correcting Tool-Use Errors in Dialogue Systems
di: Hamad, Hassan, et al.
Pubblicazione: (2025)

SAQ: Stabilizer-Aware Quantum Error Correction Decoder
di: Zenati, David, et al.
Pubblicazione: (2025)

Adapting LLMs for Minimal-edit Grammatical Error Correction
di: Staruch, Ryszard, et al.
Pubblicazione: (2025)

Evaluating LLM Reasoning Beyond Correctness and CoT
di: Abbasloo, Soheil
Pubblicazione: (2025)

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
di: Tie, Guiyao, et al.
Pubblicazione: (2025)

Internalized Self-Correction for Large Language Models
di: Upadhyaya, Nishanth, et al.
Pubblicazione: (2024)

Score Based Error Correcting Code Decoder
di: Helvits, Alon, et al.
Pubblicazione: (2026)

Adversarial Error Correction for Visual Autoregressive Generation
di: Bi, Ligong, et al.
Pubblicazione: (2026)

Improving Model Safety by Targeted Error Correction
di: Mohammadi-Seif, Abolfazl, et al.
Pubblicazione: (2026)