Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2509.07676 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915486587944960 |
|---|---|
| author | Li, Jipeng Gao, Zeyu Qi, Yubin Dong, Hande Chen, Weijian Lin, Qiang |
| author_facet | Li, Jipeng Gao, Zeyu Qi, Yubin Dong, Hande Chen, Weijian Lin, Qiang |
| contents | Large Language Models (LLMs) have achieved remarkable performance across diverse tasks, yet their susceptibility to generating incorrect content during inference remains a critical unsolved challenge. While self-correction methods offer potential solutions, their effectiveness is hindered by two inherent limitations: (1) the absence of reliable guidance signals for error localization, and (2) the restricted reasoning depth imposed by conventional next-token decoding paradigms. To address these issues, we propose Feedback-Triggered Regeneration (FTR), a novel framework that synergizes user feedback with enhanced decoding dynamics. Specifically, FTR activates response regeneration only upon receiving negative user feedback, thereby circumventing error propagation from faulty self-assessment while preserving originally correct outputs. Furthermore, we introduce Long-Term Multipath (LTM) decoding, which enables systematic exploration of multiple reasoning trajectories through delayed sequence evaluation, effectively overcoming the myopic decision-making characteristic of standard next-token prediction. Extensive experiments on mathematical reasoning and code generation benchmarks demonstrate that our framework achieves consistent and significant improvements over state-of-the-art prompt-based self-correction methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07676 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding Li, Jipeng Gao, Zeyu Qi, Yubin Dong, Hande Chen, Weijian Lin, Qiang Artificial Intelligence Large Language Models (LLMs) have achieved remarkable performance across diverse tasks, yet their susceptibility to generating incorrect content during inference remains a critical unsolved challenge. While self-correction methods offer potential solutions, their effectiveness is hindered by two inherent limitations: (1) the absence of reliable guidance signals for error localization, and (2) the restricted reasoning depth imposed by conventional next-token decoding paradigms. To address these issues, we propose Feedback-Triggered Regeneration (FTR), a novel framework that synergizes user feedback with enhanced decoding dynamics. Specifically, FTR activates response regeneration only upon receiving negative user feedback, thereby circumventing error propagation from faulty self-assessment while preserving originally correct outputs. Furthermore, we introduce Long-Term Multipath (LTM) decoding, which enables systematic exploration of multiple reasoning trajectories through delayed sequence evaluation, effectively overcoming the myopic decision-making characteristic of standard next-token prediction. Extensive experiments on mathematical reasoning and code generation benchmarks demonstrate that our framework achieves consistent and significant improvements over state-of-the-art prompt-based self-correction methods. |
| title | Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.07676 |