# Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

arXiv: https://arxiv.org/abs/2608.03123 · HTML: https://mlsanity.com/paper/2608.03123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 16 of its 27 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning](https://mlsanity.com/paper/2410.07163/) (2024)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformation](https://mlsanity.com/paper/2405.14407/) (2024)
- [Effective Instruction Parsing Plugin for Complex Logical Query Answering on Knowledge Graphs](https://mlsanity.com/paper/2410.20321/) (2024)
- [Attention Smoothing Is All You Need For Unlearning](https://mlsanity.com/paper/2603.01285/) (2026)
- [GraphRAG-Induced Dual Knowledge Structure Graphs for Personalized Learning Path Recommendation](https://mlsanity.com/paper/2506.22303/) (2025)
- [Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities](https://mlsanity.com/paper/2508.01290/) (2025)
- [CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering](https://mlsanity.com/paper/2607.24236/) (2026)

## Abstract (arXiv)

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.