Although large language models (LLMs) have achieved remarkable performance across various tasks, they remain prone to errors. A key challenge is enabling them to self-correct. While prior research has relied on external tools or large proprietary models, this work explores self-correction in small language models (SLMs) through iterative fine-tuning using solely self-generated data. We introduce the Self-Taught Self-Correction (STaSC) algorithm, which incorporates multiple algorithmic design choices. Experimental results on a question-answering task demonstrate that STaSC effectively learns self-correction, leading to significant performance improvements. Our analysis further provides insights into the mechanisms of self-correction and the impact of different design choices on learning dynamics and overall performance. To support future research, we release our user-friendly codebase and lightweight models.
View on arXiv@article{moskvoretskii2025_2503.08681,
title={ Self-Taught Self-Correction for Small Language Models },
author={ Viktor Moskvoretskii and Chris Biemann and Irina Nikishina },
journal={arXiv preprint arXiv:2503.08681},
year={ 2025 }
}