Saved in:
Bibliographic Details
Main Authors: Wu, Jiawei, Zhou, Doudou
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.00364
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914533249908736
author Wu, Jiawei
Zhou, Doudou
author_facet Wu, Jiawei
Zhou, Doudou
contents Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens despite only a subset encoding the knowledge targeted for removal. This introduces gradient noise, degrades utility, and leads to suboptimal forgetting. We propose TokenUnlearn, a token-level attribution framework that identifies and selectively targets critical tokens. Our approach combines knowledge-aware signals via masking, and entropy-aware signals to yield importance scores for precise token selection. We develop two complementary strategies: hard selection, applying unlearning only to high-importance tokens, and soft weighting, modulating gradient contributions based on importance scores. Both extend existing methods to token-level variants. Theoretical analysis shows token-level selection improves gradient signal-to-noise ratio. Experiments on TOFU and WMDP benchmarks across three model architectures demonstrate consistent improvements over sequence-level baselines in both forgetting effectiveness and utility preservation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00364
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
Wu, Jiawei
Zhou, Doudou
Computation and Language
Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens despite only a subset encoding the knowledge targeted for removal. This introduces gradient noise, degrades utility, and leads to suboptimal forgetting. We propose TokenUnlearn, a token-level attribution framework that identifies and selectively targets critical tokens. Our approach combines knowledge-aware signals via masking, and entropy-aware signals to yield importance scores for precise token selection. We develop two complementary strategies: hard selection, applying unlearning only to high-importance tokens, and soft weighting, modulating gradient contributions based on importance scores. Both extend existing methods to token-level variants. Theoretical analysis shows token-level selection improves gradient signal-to-noise ratio. Experiments on TOFU and WMDP benchmarks across three model architectures demonstrate consistent improvements over sequence-level baselines in both forgetting effectiveness and utility preservation.
title Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
topic Computation and Language
url https://arxiv.org/abs/2605.00364