# Representation-Guided Parameter-Efficient LLM Unlearning

arXiv: https://arxiv.org/abs/2604.17396 · HTML: https://mlsanity.com/paper/2604.17396/

## 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 19 Apr 2026.

## Placed in

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

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

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [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)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning](https://mlsanity.com/paper/2410.07163/) (2024)
- [Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs](https://mlsanity.com/paper/2408.06621/) (2024)
- [Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning](https://mlsanity.com/paper/2508.21300/) (2025)
- [SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA](https://mlsanity.com/paper/2505.23724/) (2025)
- [Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem](https://mlsanity.com/paper/2604.14808/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning methods have shown promise, they still struggle with the forget-retain trade-off. This can be attributed to their reliance on parameter importance metrics to identify parameters that are important exclusively for the forget set, which is fundamentally limited by the superposition phenomenon. Due to the polysemantic nature of LLM parameters, such an importance metric may struggle to disentangle parameters associated with the forget and retain sets. In this work, we propose Representation-Guided Low-rank Unlearning (REGLU), a novel approach that leverages the geometric properties of representation spaces to achieve robust and precise unlearning. First, we develop a representation-guided initialization for LoRA that identifies the optimal subspace for selective forgetting. Second, we introduce a regularization loss that constrains the outputs of the LoRA update to lie in the orthogonal complement of the retain set's representation subspace, thereby minimizing interference with the model's performance on the retain set. We evaluate REGLU on the TOFU and WMDP benchmarks across multiple models. Our results demonstrate that REGLU consistently outperforms state-of-the-art baselines, achieving superior unlearning quality while maintaining higher model utility.