@inproceedings{su-etal-2026-instructdiff,
    title = "{I}nstruct{D}iff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient {LLM} Fine-Tuning",
    author = "Su, Junyou  and
      Zhu, He  and
      Luo, Xiao  and
      Zhang, Liyu  and
      Zhou, Hong-Yu  and
      Chen, Yun  and
      Li, Peng  and
      Liu, Yang  and
      Chen, Guanhua",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.486/",
    pages = "10630--10648",
    ISBN = "979-8-89176-390-6",
    abstract = "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 reasoning tasks, and vice versa. We observe that measuring contrastive entropy between base models and minimally instruction-tuned calibrated models reveals a pattern{---}samples with the lowest contrastive entropy consistently yield optimal performance across domains, yet this principle manifests domain-adaptively: reasoning tasks favor entropy increase (cognitive expansion), while general tasks favor entropy decrease (cognitive compression). We introduce InstructDiff, a unified framework that operationalizes contrastive entropy as a domain-adaptive selection criterion through warmup calibration, bi-directional NLL filtering, and entropy-based ranking. Extensive experiments show that InstructDiff achieves 17{\%} relative improvement over full data training on mathematical reasoning and 52{\%} for general instruction-following, outperforming prior baselines while using only 10{\%} of the data."
}