# Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

arXiv: https://arxiv.org/abs/2408.06621 · HTML: https://mlsanity.com/paper/2408.06621/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 52 of its 65 references that are in the map.
- First posted on arXiv 13 Aug 2024.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 52)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning](https://mlsanity.com/paper/2012.13255/) (2020)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Measuring the Intrinsic Dimension of Objective Landscapes](https://mlsanity.com/paper/1804.08838/) (2018)

## Built on by (most cited first, 30 of 36)

- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Leak@k: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding](https://mlsanity.com/paper/2511.04934/) (2025)
- [LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples](https://mlsanity.com/paper/2512.07375/) (2025)
- [Agentic Unlearning: When LLM Agent Meets Machine Unlearning](https://mlsanity.com/paper/2602.17692/) (2026)
- [Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning](https://mlsanity.com/paper/2508.21300/) (2025)
- [Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting](https://mlsanity.com/paper/2510.17210/) (2025)
- [Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check](https://mlsanity.com/paper/2510.12981/) (2025)
- [Practical Continual Forgetting for Pre-trained Vision Models](https://mlsanity.com/paper/2501.09705/) (2025)
- [Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols](https://mlsanity.com/paper/2507.19894/) (2025)
- [Reinforcement Unlearning via Group Relative Policy Optimization](https://mlsanity.com/paper/2601.20568/) (2026)
- [REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop](https://mlsanity.com/paper/2602.06248/) (2026)
- [Knowledge Vector Weakening: Efficient Training-free Unlearning for Large Vision-Language Models](https://mlsanity.com/paper/2601.21794/) (2026)
- [Inference-time Unlearning Using Conformal Prediction](https://mlsanity.com/paper/2602.03787/) (2026)
- [Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens](https://mlsanity.com/paper/2604.17785/) (2026)
- [Towards Irreversible Machine Unlearning for Diffusion Models](https://mlsanity.com/paper/2512.03564/) (2025)
- [Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning](https://mlsanity.com/paper/2601.15595/) (2026)
- [Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning](https://mlsanity.com/paper/2602.19612/) (2026)
- [U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation](https://mlsanity.com/paper/2602.23400/) (2026)
- [GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics](https://mlsanity.com/paper/2604.02830/) (2026)
- [Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models](https://mlsanity.com/paper/2506.11253/) (2025)
- [Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictors](https://mlsanity.com/paper/2508.03245/) (2025)
- [FiCABU: A Fisher-Based, Context-Adaptive Machine Unlearning Processor for Edge AI](https://mlsanity.com/paper/2511.05605/) (2025)
- [Shadow Unlearning: A Neuro-Semantic Approach to Fidelity-Preserving Faceless Forgetting in LLMs](https://mlsanity.com/paper/2601.04275/) (2026)
- [textbfAGTAO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality](https://mlsanity.com/paper/2602.01703/) (2026)
- [EvoMU: Evolutionary Machine Unlearning](https://mlsanity.com/paper/2602.02139/) (2026)
- [Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation](https://mlsanity.com/paper/2602.05339/) (2026)
- [Representation-Guided Parameter-Efficient LLM Unlearning](https://mlsanity.com/paper/2604.17396/) (2026)
- [SoK: Unlearnability and Unlearning for Model Dememorization](https://mlsanity.com/paper/2605.11592/) (2026)
- [Interference-Aware Multi-Task Unlearning](https://mlsanity.com/paper/2605.19042/) (2026)
- [MAAT: Multi-phase Adapter-Aware Targeted Unlearning](https://mlsanity.com/paper/2605.30514/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated strong reasoning and memorization capabilities via pretraining on massive textual corpora. However, this poses risk of privacy and copyright violations, highlighting the need for efficient machine unlearning methods that remove sensitive data without retraining from scratch. While Gradient Ascent (GA) is commonly used to unlearn by reducing the likelihood of generating unwanted content, it leads to unstable optimization and catastrophic forgetting of retrained knowledge. We find that combining GA with low-rank adaptation results in poor trade-offs between computational cost and generative performance. To address these challenges, we propose Low-rank Knowledge Unlearning (LoKU), a novel framework that enables robust and efficient unlearning for LLMs. First, we introduce Inverted Hinge Loss, which suppresses unwanted tokens while maintaining fluency by boosting the probability of the next most likely token. Second, we develop a data-adaptive initialization for LoRA adapters via low-rank approximation weighted with relative Fisher information, thereby focusing updates on parameters critical for removing targeted knowledge. Experiments on the Training Data Extraction Challenge dataset using GPT-Neo models as well as on the TOFU benchmark with Phi-1.5B and Llama2-7B models demonstrate that our approach effectively removes sensitive information while maintaining reasoning and generative capabilities with minimal impact. Our implementation can be found in https://github.com/csm9493/efficient-llm-unlearning.