@inproceedings{wang-zhao-2026-tare,
    title = "{TARE}: Lightweight Token-Aware Representation Editing for Fine-tuning Transformer-like Models",
    author = "Wang, Yulong  and
      Zhao, Siyu",
    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.841/",
    pages = "18452--18471",
    ISBN = "979-8-89176-390-6",
    abstract = "Parameter-efficient fine-tuning (PEFT) must balance effectiveness and efficiency: low-rank methods can be costly, while global representation edits often underfit token-level contexts. We propose **Token-Aware Representation Editing (TARE)**, a PEFT method that performs fine-grained, token-specific edits with a small additional inference overhead and minimal tuning.After each FFN block in a transformer-like model, we adopt a lightweight selector that scores a small pool of hidden representation editors for each token, activates only the top-k editors, and mixes their element-wise scaling/bias updates. This design achieves superior performance while maintaining computational efficiency, yielding a more favorable Pareto frontier compared to state-of-the-art (SOTA) methods.Across LLaMA-3-8B (eight knowledge reasoning and seven mathematical reasoning tasks) and RoBERTa-base/large (GLUE), TARE outperforms SOTAs (LoRA, DoRA, MiLoRA, LoReFT, and RED), achieving 86.7{\%} (knowledge reasoning), 76.7{\%} (mathematical reasoning), and 88.3{\%} (GLUE) while tuning only 0.0392{\%} of parameters using about 20 GiB peak GPU memory during training.An implementation is available at: {\ensuremath{<}}https://github.com/PatriciaPulec/tare{\ensuremath{>}}."
}