Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.17305 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914575149957120 |
|---|---|
| author | Wu, Yuning Liu, Yingmin Shu, Yang |
| author_facet | Wu, Yuning Liu, Yingmin Shu, Yang |
| contents | Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outputs -- remains largely ad hoc, relying on generic prompts such as "please reconsider your answer" without systematic error analysis or convergence guarantees. We propose CyberCorrect, a framework that formalizes LLM self-correction as a closed-loop control system grounded in cybernetic theory. The framework models the LLM generator as the plant and introduces a tri-modal Error Detector (combining self-consistency, verbalized confidence, and logic-chain verification) as the sensor. A type-directed Correction Controller generates targeted repair instructions based on diagnosed error categories, while a Convergence Judge determines iteration termination using stability criteria adapted from control theory. We further introduce three control-theoretic evaluation metrics -- convergence rate, overshoot rate, and oscillation rate -- that capture correction dynamics beyond final accuracy. Experiments on our constructed CyberCorrect-Bench (440 reasoning tasks with annotated error types and correction paths) show that CyberCorrect achieves 79.8% final accuracy, improving upon the best existing self-correction method by 6.2 percentage points, while reducing overshoot (erroneous over-correction) by 41% through its convergence control mechanism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17305 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models Wu, Yuning Liu, Yingmin Shu, Yang Artificial Intelligence Computation and Language Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outputs -- remains largely ad hoc, relying on generic prompts such as "please reconsider your answer" without systematic error analysis or convergence guarantees. We propose CyberCorrect, a framework that formalizes LLM self-correction as a closed-loop control system grounded in cybernetic theory. The framework models the LLM generator as the plant and introduces a tri-modal Error Detector (combining self-consistency, verbalized confidence, and logic-chain verification) as the sensor. A type-directed Correction Controller generates targeted repair instructions based on diagnosed error categories, while a Convergence Judge determines iteration termination using stability criteria adapted from control theory. We further introduce three control-theoretic evaluation metrics -- convergence rate, overshoot rate, and oscillation rate -- that capture correction dynamics beyond final accuracy. Experiments on our constructed CyberCorrect-Bench (440 reasoning tasks with annotated error types and correction paths) show that CyberCorrect achieves 79.8% final accuracy, improving upon the best existing self-correction method by 6.2 percentage points, while reducing overshoot (erroneous over-correction) by 41% through its convergence control mechanism. |
| title | CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.17305 |