# Dissecting Fine-Tuning Unlearning in Large Language Models

arXiv: https://arxiv.org/abs/2410.06606 · HTML: https://mlsanity.com/paper/2410.06606/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://mlsanity.com/paper/2402.00159/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity](https://mlsanity.com/paper/2401.01967/) (2024)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities](https://mlsanity.com/paper/2308.12833/) (2023)
- [Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge](https://mlsanity.com/paper/2404.05880/) (2024)
- [Dissecting Language Models: Machine Unlearning via Selective Pruning](https://mlsanity.com/paper/2403.01267/) (2024)
- [Digital Forgetting in Large Language Models: A Survey of Unlearning Methods](https://mlsanity.com/paper/2404.02062/) (2024)
- [Localizing Paragraph Memorization in Language Models](https://mlsanity.com/paper/2403.19851/) (2024)
- [Intrinsic Test of Unlearning Using Parametric Knowledge Traces](https://mlsanity.com/paper/2406.11614/) (2024)
- [Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching](https://mlsanity.com/paper/2405.13820/) (2024)

## Built on by (most cited first, 26 of 26)

- [Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models](https://mlsanity.com/paper/2508.10599/) (2025)
- [Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning](https://mlsanity.com/paper/2502.09022/) (2025)
- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples](https://mlsanity.com/paper/2512.07375/) (2025)
- [Contrastive Representation Shaping for LLM Unlearning](https://mlsanity.com/paper/2601.22028/) (2026)
- [Towards Multi-dimensional Explanation Alignment for Medical Classification](https://mlsanity.com/paper/2410.21494/) (2024)
- [Controlling Repetition in Protein Language Models](https://mlsanity.com/paper/2602.00782/) (2026)
- [Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2512.17911/) (2025)
- [Alignment midtraining for animals](https://mlsanity.com/paper/2604.13076/) (2026)
- [KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning](https://mlsanity.com/paper/2510.02392/) (2025)
- [Understanding and Enforcing Weight Disentanglement in Task Arithmetic](https://mlsanity.com/paper/2604.17078/) (2026)
- [ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs](https://mlsanity.com/paper/2512.09953/) (2025)
- [KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models](https://mlsanity.com/paper/2602.19275/) (2026)
- [Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility](https://mlsanity.com/paper/2606.03291/) (2026)
- [Understanding Machine Unlearning Through the Lens of Mode Connectivity](https://mlsanity.com/paper/2504.06407/) (2025)
- [The Rise of Parameter Specialization for Knowledge Storage in Large Language Models](https://mlsanity.com/paper/2505.17260/) (2025)
- [Forgetting-MarI: LLM Unlearning via Marginal Information Regularization](https://mlsanity.com/paper/2511.11914/) (2025)
- [Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models](https://mlsanity.com/paper/2602.00300/) (2026)
- [Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic Data](https://mlsanity.com/paper/2601.23153/) (2026)
- [EvoMU: Evolutionary Machine Unlearning](https://mlsanity.com/paper/2602.02139/) (2026)
- [Structural Disentanglement in Bilinear MLPs via Architectural Inductive Bias](https://mlsanity.com/paper/2602.05635/) (2026)
- [Fast Unlearning at Scale via Margin Self-Correction](https://mlsanity.com/paper/2606.02920/) (2026)
- [Understanding Machine Unlearning Through the Lens of Mode Connectivity](https://mlsanity.com/paper/2607.23970/) (2026)
- [CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models](https://mlsanity.com/paper/2609.20267/) (2026)
- [The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning](https://mlsanity.com/paper/2609.29045/) (2026)
- [Learning What to Forget: Distributional Unlearning for LLM Representation Spaces](https://mlsanity.com/paper/2609.38929/) (2026)

## Abstract (arXiv)

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is unclear. In this work, we delve into the limitations of fine-tuning-based unlearning through activation patching and parameter restoration experiments. Our findings reveal that these methods alter the model's knowledge retrieval process, providing further evidence that they do not genuinely erase the problematic knowledge embedded in the model parameters. Instead, the coefficients generated by the MLP components in the model's final layer are the primary contributors to these seemingly positive unlearning effects, playing a crucial role in controlling the model's behaviors. Furthermore, behavioral tests demonstrate that this unlearning mechanism inevitably impacts the global behavior of the models, affecting unrelated knowledge or capabilities. The code is released at https://github.com/yihuaihong/Dissecting-FT-Unlearning.