# Multi-Objective Large Language Model Unlearning

arXiv: https://arxiv.org/abs/2412.20412 · HTML: https://mlsanity.com/paper/2412.20412/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 19 of its 32 references that are in the map.
- First posted on arXiv 29 Dec 2024.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Orthogonal Gradient Descent for Continual Learning](https://mlsanity.com/paper/1910.07104/) (2019)
- [Formalizing and Benchmarking Prompt Injection Attacks and Defenses](https://mlsanity.com/paper/2310.12815/) (2023)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Unlearn What You Want to Forget: Efficient Unlearning for LLMs](https://mlsanity.com/paper/2310.20150/) (2023)
- [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://mlsanity.com/paper/2207.05521/) (2022)
- [Copyright Traps for Large Language Models](https://mlsanity.com/paper/2402.09363/) (2024)
- [EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models](https://mlsanity.com/paper/2402.09801/) (2024)
- [nabla τ: Gradient-based and Task-Agnostic machine Unlearning](https://mlsanity.com/paper/2403.14339/) (2024)
- [Random Relabeling for Efficient Machine Unlearning](https://mlsanity.com/paper/2305.12320/) (2023)
- [A More Practical Approach to Machine Unlearning](https://mlsanity.com/paper/2406.09391/) (2024)

## Built on by (most cited first, 7 of 7)

- [Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models](https://mlsanity.com/paper/2506.05314/) (2025)
- [Mitigating Biases in Language Models via Bias Unlearning](https://mlsanity.com/paper/2509.25673/) (2025)
- [Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols](https://mlsanity.com/paper/2507.19894/) (2025)
- [A Survey on Unlearning in Large Language Models](https://mlsanity.com/paper/2510.25117/) (2025)
- [Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization](https://mlsanity.com/paper/2509.20230/) (2025)
- [MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2602.23798/) (2026)
- [Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation](https://mlsanity.com/paper/2604.15482/) (2026)

## Abstract (arXiv)

Machine unlearning in the domain of large language models (LLMs) has attracted great attention recently, which aims to effectively eliminate undesirable behaviors from LLMs without full retraining from scratch. In this paper, we explore the Gradient Ascent (GA) approach in LLM unlearning, which is a proactive way to decrease the prediction probability of the model on the target data in order to remove their influence. We analyze two challenges that render the process impractical: gradient explosion and catastrophic forgetting. To address these issues, we propose Multi-Objective Large Language Model Unlearning (MOLLM) algorithm. We first formulate LLM unlearning as a multi-objective optimization problem, in which the cross-entropy loss is modified to the unlearning version to overcome the gradient explosion issue. A common descent update direction is then calculated, which enables the model to forget the target data while preserving the utility of the LLM. Our empirical results verify that MoLLM outperforms the SOTA GA-based LLM unlearning methods in terms of unlearning effect and model utility preservation. The source code is available at https://github.com/zibinpan/MOLLM.