# Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond

arXiv: https://arxiv.org/abs/2502.19301 · HTML: https://mlsanity.com/paper/2502.19301/

## Key facts

- Cited by 61 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 33 of its 37 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## 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 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [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)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Do Membership Inference Attacks Work on Large Language Models?](https://mlsanity.com/paper/2402.07841/) (2024)
- [Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks](https://mlsanity.com/paper/2309.17410/) (2023)
- [Provably Robust DPO: Aligning Language Models with Noisy Feedback](https://mlsanity.com/paper/2403.00409/) (2024)
- [Reinforcement Learning for LLM Post-Training: A Survey](https://mlsanity.com/paper/2407.16216/) (2024)

## Built on by (most cited first, 30 of 61)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics](https://mlsanity.com/paper/2506.12618/) (2025)
- [Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning](https://mlsanity.com/paper/2505.11953/) (2025)
- [From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?](https://mlsanity.com/paper/2506.08295/) (2025)
- [LLM Unlearning with LLM Beliefs](https://mlsanity.com/paper/2510.19422/) (2025)
- [GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs](https://mlsanity.com/paper/2503.09117/) (2025)
- [SoK: Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2506.09227/) (2025)
- [Self-Destructive Language Model](https://mlsanity.com/paper/2505.12186/) (2025)
- [Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models](https://mlsanity.com/paper/2506.05314/) (2025)
- [LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples](https://mlsanity.com/paper/2512.07375/) (2025)
- [Attention Smoothing Is All You Need For Unlearning](https://mlsanity.com/paper/2603.01285/) (2026)
- [Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning](https://mlsanity.com/paper/2602.06441/) (2026)
- [UniErase: Towards Balanced and Precise Unlearning in Language Models](https://mlsanity.com/paper/2505.15674/) (2025)
- [The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation](https://mlsanity.com/paper/2512.19025/) (2025)
- [Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation](https://mlsanity.com/paper/2505.06027/) (2025)
- [Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack](https://mlsanity.com/paper/2506.01318/) (2025)
- [Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning](https://mlsanity.com/paper/2508.04329/) (2025)
- [Towards Understanding Valuable Preference Data for Large Language Model Alignment](https://mlsanity.com/paper/2510.13212/) (2025)
- [A Survey on Unlearning in Large Language Models](https://mlsanity.com/paper/2510.25117/) (2025)
- [Geometric-disentangelment Unlearning](https://mlsanity.com/paper/2511.17100/) (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)
- [Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models](https://mlsanity.com/paper/2510.17620/) (2025)
- [Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2601.22020/) (2026)
- [RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair](https://mlsanity.com/paper/2604.12820/) (2026)
- [GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models](https://mlsanity.com/paper/2506.10946/) (2025)
- [Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models](https://mlsanity.com/paper/2508.08875/) (2025)
- [Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning](https://mlsanity.com/paper/2510.00125/) (2025)
- [What Is Preference Optimization Doing, and Why?](https://mlsanity.com/paper/2512.00778/) (2025)
- [Per-parameter Task Arithmetic for Unlearning in Large Language Models](https://mlsanity.com/paper/2601.22030/) (2026)

## Abstract (arXiv)

Large language models (LLMs) should undergo rigorous audits to identify potential risks, such as copyright and privacy infringements. Once these risks emerge, timely updates are crucial to remove undesirable responses, ensuring legal and safe model usage. It has spurred recent research into LLM unlearning, focusing on erasing targeted undesirable knowledge without compromising the integrity of other, non-targeted responses. Existing studies have introduced various unlearning objectives to pursue LLM unlearning without necessitating complete retraining. However, each of these objectives has unique properties, and no unified framework is currently available to comprehend them thoroughly. To fill the gap, we propose a toolkit of the gradient effect (G-effect), quantifying the impacts of unlearning objectives on model performance from a gradient perspective. A notable advantage is its broad ability to detail the unlearning impacts from various aspects across instances, updating steps, and LLM layers. Accordingly, the G-effect offers new insights into identifying drawbacks of existing unlearning objectives, further motivating us to explore a series of new solutions for their mitigation and improvements. Finally, we outline promising directions that merit further studies, aiming at contributing to the community to advance this important field.