Cover Image

Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Aofan, Meng, Jingxiang
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs
by: Liu, Aofan, et al.
Published: (2026)

VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commands
by: Liu, Aofan, et al.
Published: (2025)

Decoding Emotion in the Deep: A Systematic Study of How LLMs Represent, Retain, and Express Emotion
by: Zhang, Jingxiang, et al.
Published: (2025)

Error-Feedback Model for Output Correction in Bilateral Control-Based Imitation Learning
by: Sato, Hiroshi, et al.
Published: (2024)

Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding
by: Li, Jipeng, et al.
Published: (2025)

Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs
by: Liu, Xuyuan, et al.
Published: (2025)

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

CAP: Controllable Alignment Prompting for Unlearning in LLMs
by: Wang, Zhaokun, et al.
Published: (2026)

RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
by: Liu, Aofan, et al.
Published: (2025)

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

Structure Enables Effective Self-Localization of Errors in LLMs
by: Samanta, Ankur, et al.
Published: (2026)

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

Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
by: Lee, Yu-Ting, et al.
Published: (2025)

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

Route-Induced Density and Stability (RIDE): Controlled Intervention and Mechanism Analysis of Routing-Style Meta Prompts on LLM Internal States
by: Zhang, Dianxing, et al.
Published: (2026)

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

A Systematic Analysis of Large Language Models with RAG-enabled Dynamic Prompting for Medical Error Detection and Correction
by: Ahmed, Farzad, et al.
Published: (2025)

Leveraging LLMs for Bangla Grammar Error Correction:Error Categorization, Synthetic Data, and Model Evaluation
by: Bhattacharyya, Pramit, et al.
Published: (2024)

LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERT
by: Xu, Zhenyu, et al.
Published: (2024)

Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework
by: Ma, Xilai, et al.
Published: (2026)

LLMs are Superior Feedback Providers: Bootstrapping Reasoning for Lie Detection with Self-Generated Feedback
by: Banerjee, Tanushree, et al.
Published: (2024)

Organic Data-Driven Approach for Turkish Grammatical Error Correction and LLMs
by: Ersoy, Asım, et al.
Published: (2024)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
by: Kang, Diancheng, et al.
Published: (2026)

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning
by: Yu, Erxin, et al.
Published: (2025)

Efficient and Universal Neural-Network Decoder for Stabilizer-Based Quantum Error Correction
by: Hu, Gengyuan, et al.
Published: (2025)

Neural Internal Model Control: Learning a Robust Control Policy via Predictive Error Feedback
by: Gao, Feng, et al.
Published: (2024)

Self-Corrective Task Planning by Inverse Prompting with Large Language Models
by: Lee, Jiho, et al.
Published: (2025)

Stepwise Reasoning Error Disruption Attack of LLMs
by: Peng, Jingyu, et al.
Published: (2024)

Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis
by: Zou, Rui, et al.
Published: (2025)

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

Prompt-Based Length Controlled Generation with Multiple Control Types
by: Jie, Renlong, et al.
Published: (2024)

LoopGuard: Breaking Self-Reinforcing Attention Loops via Dynamic KV Cache Intervention
by: Xu, Dongjie, et al.
Published: (2026)

"When Data is Scarce, Prompt Smarter"... Approaches to Grammatical Error Correction in Low-Resource Settings
by: De, Somsubhra, et al.
Published: (2025)

Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification
by: Liu, Aofan, et al.
Published: (2025)

Prompt Optimization with Human Feedback
by: Lin, Xiaoqiang, et al.
Published: (2024)

Test-time Prompt Intervention
by: Yang, Chenxu, et al.
Published: (2025)

Intention Chain-of-Thought Prompting with Dynamic Routing for Code Generation
by: Li, Shen, et al.
Published: (2025)

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

SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation
by: Yang, Chengyi, et al.
Published: (2026)

APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification
by: Chernodub, Artem, et al.
Published: (2025)