一作ACL 2026Findings· Findings of ACL
GALA : Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training
Zhongwei Xie · Ruihao Liao · Zimo Wang · Chong Chen · Xian-Sheng Hua · Xiao Luo
摘要
Self-training has emerged as a promising direction for autonomously improving large language models (LLMs). Existing approaches typically adopt a \textit{generate-and-filter} paradigm based on rejection sampling, which could suffer from inefficiency and low-quality reasoning paths. Towards this e...