@inproceedings{steele-2026-annotation,
    title = "Annotation Entropy Predicts Per-Example Learning Dynamics in {L}o{RA} Fine-Tuning",
    author = "Steele, Brady",
    editor = "T.Y.S.S., Santosh  and
      Rodriguez, Juan Diego  and
      de Gibert, Ona",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-srw.11/",
    pages = "129--141",
    ISBN = "979-8-89176-393-7",
    abstract = "Annotator disagreement on tasks like natural languageinference (NLI) reflects genuine linguistic ambiguity,yet most fine-tuning recipes treat every example as equallylearnable.We ask whether this external signal of ambiguity predicts*per-example* learning dynamics under LoRA, the most widelyused parameter-efficient fine-tuning method, and find that it does.Correlating annotation entropy (from ChaosNLI{'}s 100 labels perexample) with per-example area under the loss curve (AULC)on SNLI and MNLI, the correlation is positive in all 25conditions tested (Spearman $\rho {=} 0.06$-0.43), withdecoder-only models showing stronger correlations thanencoders at matched LoRA rank.More strikingly, under LoRA contested examples exhibit*un-learning*: their gold-label loss *increases*during training, a pattern that is largely absent underfull fine-tuning and IA$^3$ in the encoder setting wherematched comparisons are available, and that we also observeunder LoRA on two decoder-only models.The effect survives partial-correlation controls andreplicates across seeds and datasets.A preliminary noise-injection experiment is consistentwith these findings."
}