Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding
This addresses a critical unsolved challenge in making LLMs more reliable for practical applications, though it appears to be an incremental improvement over existing self-correction methods.
The paper tackles the problem of LLMs generating incorrect content during inference by proposing Feedback-Triggered Regeneration (FTR) with Long-Term Multipath decoding, achieving consistent and significant improvements over state-of-the-art prompt-based self-correction methods on mathematical reasoning and code generation benchmarks.
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.