超越输出批评：通过任务蒸馏实现自我纠正
Beyond Output Critique: Self-Correction via Task Distillation
AI总结：
SELF-THOUGHT通过任务蒸馏引入任务抽象步骤，提升大型和小型语言模型的自我纠正能力，提高准确性和鲁棒性。
摘要：
大型语言模型（LLMs）在自我纠正能力方面表现出潜力，其中迭代细化提高了生成响应的质量。然而，现有大多数方法在输出批评层面操作，仅能修补表面错误，而难以纠正深层次的推理缺陷。我们提出了SELF-THOUGHT框架，该框架在解决方案细化之前引入了任务抽象的中间步骤。给定输入和初始响应，模型首先将任务蒸馏成一个结构化的模板，该模板捕捉了关键变量、约束和问题结构。这种抽象随后指导解决方案的实例化，使后续响应基于对任务的更清晰理解，从而减少错误传播。关键在于，我们展示了这些抽象可以跨模型转移：由大型模型生成的模板可以作为结构化指南指导小型LLM，后者通常难以实现内在自我纠正。通过重用蒸馏的任务结构，小型模型在无需大量微调或依赖外部验证器的情况下实现了更可靠的细化。在多样化的推理任务中，SELF-THOUGHT提高了准确性、鲁棒性和泛化能力，为更可靠的自我纠正语言系统提供了可扩展的路径。
英文摘要：
Large language models (LLMs) have shown promising self-correction abilities, where iterative refinement improves the quality of generated responses. However, most existing approaches operate at the level of output critique, patching surface errors while often failing to correct deeper reasoning flaws. We propose SELF-THOUGHT, a framework that introduces an intermediate step of task abstraction before solution refinement. Given an input and an initial response, the model first distills the task into a structured template that captures key variables, constraints, and problem structure. This abstraction then guides solution instantiation, grounding subsequent responses in a clearer understanding of the task and reducing error propagation. Crucially, we show that these abstractions can be transferred across models: templates generated by larger models can serve as structured guides for smaller LLMs, which typically struggle with intrinsic self-correction. By reusing distilled task structures, smaller models achieve more reliable refinements without heavy fine-tuning or reliance on external verifiers. Experiments across diverse reasoning tasks demonstrate that SELF-THOUGHT improves accuracy, robustness, and generalization for both large and small models, offering a scalable path toward more reliable self-correcting language systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
