作者位次 #4/9ACL 2026Poster· Natural Language Processing
I nstruct D iff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient LLM Fine-Tuning
Junyou Su · He Zhu · Xiao Luo · Liyu Zhang · Hong-Yu Zhou · Yun Chen · Peng Li · Yang Liu · Guanhua Chen
摘要
Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing returns. Existing data selection methods suffer from severe domain specificity: techniques optimized for general instruction-following fail on...