Representation-Guided Parameter-Efficient LLM Unlearning

• URL: http://arxiv.org/abs/2604.17396v1
• Date: Sun, 19 Apr 2026 11:59:58 GMT
• Title: Representation-Guided Parameter-Efficient LLM Unlearning
• Abstract summary: Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques.<n>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.
• Score: 7.509597637044037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data [52.80567461420316]
  We propose a Memory-Augmented LLM-based Multi-Agent System (textbfMALMAS) for automated feature generation.<n>MALMAS decomposes the generation process into agents with distinct responsibilities, and a Router Agent activates an appropriate subset of agents per iteration.<n>We further integrate a memory module comprising procedural memory, feedback memory, and conceptual memory, enabling iterative refinement that adaptively guides subsequent feature generation.
  arXiv  Detail & Related papers  (2026-04-22T07:09:30Z)
• MeGU: Machine-Guided Unlearning with Target Feature Disentanglement [73.49657372882082]
  We propose a novel framework that guides unlearning through concept-aware re-alignment.<n>MeGU enables controlled and selective forgetting, effectively mitigating both under-unlearning and over-unlearning.
  arXiv  Detail & Related papers  (2026-02-19T05:20:31Z)
• Sparsity-Aware Unlearning for Large Language Models [20.699929903336113]
  Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks.<n>Machine unlearning has emerged as a promising solution to selectively remove such information without full retraining.<n>We find that unlearning effectiveness degrades substantially on sparse models.<n>We propose Sparsity-Aware Unlearning (SAU), which decouples unlearning from sparsification objectives through gradient masking.
  arXiv  Detail & Related papers  (2026-01-31T07:45:30Z)
• Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA [50.97792275353563]
  We introduce a novel framework that restructures a single Low-Rank Adaptation (LoRA) module as a decomposable Rank-1 Expert Pool.<n>Our method learns to dynamically compose a sparse, task-specific update by selecting from this expert pool, guided by the semantics of the [Guided] token.
  arXiv  Detail & Related papers  (2026-01-30T10:54:51Z)
• Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning [15.880906462267935]
  VILA is a novel unlearning framework that explicitly considers the assumptions overlooked in FILA.<n>We set new state-of-the-art performance on benchmarks including TOFU, WMDP, and MUSE.
  arXiv  Detail & Related papers  (2025-08-29T01:45:09Z)
• LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection [0.0]
  Existing empirical methods often yield incomplete forgetting or unintended degradation of unrelated knowledge due to poor localization.<n>GRIN introduces a novel gradient-ratio-based metric to identify parameters most responsible for memorizing forget data.<n>We then perform selective noise injection into these parameters prior to fine-tuning, which improves unlearning performance while maintaining model utility.
  arXiv  Detail & Related papers  (2025-08-08T17:15:32Z)
• Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs [15.23174472320989]
  Large Language Models (LLMs) are central to many contemporary AI applications.<n>Recent works in eXplainable AI (XAI) suggest that interpretability can also enable model compression.
  arXiv  Detail & Related papers  (2025-06-16T17:38:36Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning [105.11844150736536]
  Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. We propose a new method called MoRA, which employs a square matrix to achieve high-rank updating while maintaining the same number of trainable parameters. Our method outperforms LoRA on memory-intensive tasks and achieves comparable performance on other tasks.
  arXiv  Detail & Related papers  (2024-05-20T15:48:32Z)
• Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy [48.29181662640212]
  Factual inconsistencies pose a significant hurdle for the faithful summarization by generative models. We consolidate key error types of inconsistent facts in summaries, and incorporate them to facilitate both the zero-shot and supervised paradigms of LLMs.
  arXiv  Detail & Related papers  (2024-02-20T08:41:23Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.