Self-Correction via Task Distillation

ICLR 2026 Conference Submission20584 Authors

Keywords: Self-Correction, Large Language Model, Reasoning, Distillation

TL;DR: We show the advantages of task abstraction to self-correct the initial responses on large and small LLMs

Abstract: 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.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 20584