Skip to content
Preprint

Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

Aug 2026 · 0 citations · 27 references
Computer Science

TL;DR

The Trajectory-guided Forget-Recover Network (TFR-Net) is proposed, which separates persistent target-related channels from transient hotspots and suppresses only the persistent ones, and achieves a more favorable trade-off between unlearning effectiveness and retained utility than representative baselines.

Abstract

Machine unlearning aims to eliminate the influence of sensitive data on a model. In the real world, unlearning requests arrive continually, which gives rise to two challenges. First, an unlearning intervention may redistribute target-related computation across remaining pathways, allowing previously forgotten knowledge to re-emerge. Second, repeated unlearning interventions may progressively reduce the model capacity needed to preserve retained utility. To address these challenges, we propose the Trajectory-guided Forget-Recover Network (TFR-Net). TFR-Net tracks channel-level risk across requests. It separates persistent target-related channels from transient hotspots and suppresses only the persistent ones. TFR-Net also recovers model capacity by reactivating dormant channels. These channels make strong contributions to retained utility and show low current and historical forget risk. The recovery is accepted only when retained-utility degradation remains within a predefined tolerance. Experiments on four datasets show that TFR-Net consistently achieves a more favorable trade-off between unlearning effectiveness and retained utility than representative baselines.

View source

Similar papers

#artificial intelligence Preprint Aug 2026

On the Plasticity Collapse in Continual Machine Unlearning

It is shown that continual unlearning operations accumulate geometric constraints in parameter space, leading to saturated subspaces that restrict future updates, a critical barrier to the long-term reliability of machine unlearning systems and motivate the development of plasticity-preserving unlearning algorithms.

Ying-Dan Shi, Xiang-Dong Xu, Kai-Ze Ding et al. · 0 citations
Preprint Aug 2026

Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning

J-Access is proposed, an inference-time audit that uses the Jacobian lens to map intermediate representations into vocabulary space and measures how often target concepts remain accessible along the model's output pathway, positioning J-Access as a model-level diagnostic for assessing residual susceptibility in unlearn...

Zirui Song, Hua-Xing Liu, Xiang Wang et al. · 1 citation

Trajectory Unlearning on LLM-based Agents

Existing large language model (LLM) unlearning has focused primarily on removing specific knowledge, such as harmful facts, private data, or copyrighted content. However, as LLMs are increasingly deployed as autonomous agents, a fundamental yet overlooked problem emerges: beyond suppressing what an agent knows, an agen...

Ying-Dan Shi, Ren Wang · 0 citations

Test-Time Unlearning via Sparse Autoencoder

This work proposes ARIA (autoencoder-gated inference-time unlearning), a test-time unlearning method that leaves model weights intact and gates access to unwanted knowledge only when generation enters a forget-related state and introduces three post-unlearning adversarial attacks targeting weight-space and decoding-spa...

Ping-Zhi Li, Jinhao Duan, Vaishnav Tadiparthi et al. · 1 citation
#artificial intelligence Preprint Sep 2026

Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs

This work proposes Forgetting Only What Matters via Unlearning Layers (FOM-UL), a layer-level unlearning framework that selects transformer layers using a forget-to-retain significance score and provides an empirical path toward quantization-resilient unlearning.

Ravi Ranjan, O. Kotevska, Agoritsa Polyzou · 3 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.