LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
Abstract
Large language models (LLMs) have demonstrated remarkable progress in reasoning, often through supervised fine-tuning (SFT). However, SFT is resource-intensive, relying on large curated datasets, rejection-sampled demonstrations, and uniform optimization across all tokens, even though only a fraction carry meaningful learning value. In this work, we explore a counterintuitive idea: can smaller language models (SLMs) teach larger language models (LLMs) by revealing high-value reasoning moments that reflect the latter's unique strength? We propose LightReasoner, a novel framework that leverages the behavioral divergence between a stronger expert model (LLM) and a weaker amateur model (SLM). LightReasoner operates in two stages: (1) a sampling stage that pinpoints critical reasoning moments and constructs supervision examples capturing the expert's advantage through expert-amateur contrast, and (2) a fine-tuning stage that aligns the expert model with these distilled examples, amplifying its reasoning strengths. Across seven mathematical benchmarks, LightReasoner improves accuracy by up to 28.1%, while reducing time consumption by 90%, sampled problems by 80%, and tuned token usage by 99%, all without relying on ground-truth labels. By turning weaker SLMs into effective teaching signals, LightReasoner offers a scalable and resource-efficient approach for advancing LLM reasoning. Code is available at: https://github.com/HKUDS/LightReasoner
Cite
@article{arxiv.2510.07962,
title = {LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?},
author = {Jingyuan Wang and Yankai Chen and Zhonghang Li and Chao Huang},
journal= {arXiv preprint arXiv:2510.07962},
year = {2026}
}
Comments
Updated to ACL 2026 camera-ready version with improved method presentation, expanded related work discussion, additional analyses, and presentation refinements