一作ACL 2026Findings· Findings of ACL
Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models
Xiaomeng Hu · Yixuan Tang · Haoze Li · Hao Chen · Qi Zhang · Zhanming Shen · Yiming Zhang · Haobo Wang · Junbo Zhao
摘要
With the rapid progress of large language models (LLMs), aligning a general-purpose model with downstream tasks through fine-tuning has become a central research focus. Selecting only high-quality examples for training has been shown to be one of the most effective ways to improve fine-tuning per...