TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning

Dabiao Ma; Ziming Dai; Zhimin Xin; Shu Wang; Jian Yang; Haojun Fei

IJCAI 20260 citations

TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning

Dabiao Ma, Ziming Dai, Zhimin Xin, Shu Wang, Jian Yang, Haojun Fei

Abstract

Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: once a target module is selected, every token passing through it contributes equally to the downstream task and requires a parameter update. In this paper, we challenge this convention by revealing a pervasive token-level redundancy in the fine-tuning of large models (LMs). We propose TS-PEFT, a theoretical framework utilizing proximal optimization that acts as a dynamic probe to identify token-level redundancy during the fine-tuning process. Extensive experiments demonstrate that indiscriminately updating all tokens is not only computationally superfluous but often introduces optimization noise. Surprisingly, by discarding 30%-70% of token updates, TS-PEFT consistently matches or exceeds the performance of dense baselines such as LoRA, DoRA. Our in-depth analysis shows that the learned token-level sparsity is a superior indicator of module importance compared to traditional weight criteria, providing a novel data-driven perspective on the intrinsic adaptation mechanism of LMs.

Machine Learning: Learning sparse modelsMachine Learning: Multi-task and transfer learningNatural Language Processing: Interpretability and analysis of models for NLP

BibTeX

@inproceedings{ijcai2026_tspeftunveilingt,
  title = {TS-PEFT: Unveiling Token-Level Redundancy in Parameter-Efficient Fine-Tuning},
  author = {Dabiao Ma and Ziming Dai and Zhimin Xin and Shu Wang and Jian Yang and Haojun Fei},
  booktitle = {IJCAI 2026},
  year = {2026}
}