作者位次 #3/4ACL 2026Poster· Natural Language Processing
L ight R easoner: Can Small Language Models Teach Large Language Models Reasoning?
Jingyuan Wang · Yankai Chen · Zhonghang Li · Chao Huang
摘要
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 fract...