mlsanityData to 7 Oct 2026

Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models

arXiv 2409.13474 ↗First posted 20 Sep 2024cs.CL cs.LGcited by 32

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

also in 1 more
Abstract (arXiv)

Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely solely on negative feedback to suppress responses related to the forget set, which often results in nonsensical or inconsistent outputs, diminishing model utility and posing potential privacy risks. To address this limitation, we propose a novel approach called Alternate Preference Optimization (AltPO), which combines negative feedback with in-domain positive feedback on the forget set. Additionally, we introduce new evaluation metrics to assess the quality of responses related to the forget set. Extensive experiments show that our approach not only enables effective unlearning but also avoids undesirable model behaviors while maintaining overall model performance. Our implementation can be found at https://github.com/molereddy/Alternate-Preference-Optimization.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 21 of its 23 references that are in the map. First posted on arXiv 20 Sep 2024.

Builds on

21 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning8 Apr

Other references · 20

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2019Machine Unlearningcited by 1,020
  4. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  5. 2024TOFU: A Task of Fictitious Unlearning for LLMscited by 507
  6. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 488
  7. 2023Who's Harry Potter? Approximate Unlearning in LLMscited by 366
  8. 2020Amnesiac Machine Learningcited by 305
  9. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMscited by 211
  10. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teachercited by 189
  11. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  12. 2024Towards Safer Large Language Models through Machine Unlearningcited by 134
8 more
  1. 2024Large Language Model Unlearning via Embedding-Corrupted Promptscited by 112
  2. 2024SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearningcited by 104
  3. 2024Guardrail Baselines for Unlearning in LLMscited by 90
  4. 2024Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Differencecited by 85
  5. 2020Learn to Forget: Machine Unlearning via Neuron Maskingcited by 56
  6. 2024UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Modelscited by 49
  7. 2024Are we making progress in unlearning? Findings from the first NeurIPS unlearning competitioncited by 48
  8. 2024Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initializationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 13; 2026: 16.

32 papers.

Sort:

By area:

  1. 2024Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearningcited by 160
  2. 2025OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metricscited by 80
  3. 2024LLM Unlearning via Loss Adjustment with Only Forget Datacited by 71
  4. 2025Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMscited by 41
  5. 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearningcited by 39
  6. 2024Erasing Conceptual Knowledge from Language Modelscited by 34
  7. 2025GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detectioncited by 17
  8. 2025LLM Unlearning with LLM Beliefscited by 17
  9. 2025Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skillscited by 12
  10. 2026BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearningcited by 8
  11. 2025Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMscited by 7
  12. 2025DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoningcited by 7
20 more
  1. 2026Explainable LLM Unlearning Through Reasoningcited by 7
  2. 2026Attention Smoothing Is All You Need For Unlearningcited by 6
  3. 2026Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearningcited by 5
  4. 2025OFMU: Optimization-Driven Framework for Machine Unlearningcited by 4
  5. 2026REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loopcited by 4
  6. 2025Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearningcited by 3
  7. 2026Models Designed to Forget: Machine Unlearning via Key Deletioncited by 3
  8. 2025Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readinesscited by 2
  9. 2025Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearningcited by 2
  10. 2026STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Modelscited by 2
  11. 2025Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearningcited by 1
  12. 2026The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearningcited by 1
  13. 2026Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearningcited by 1
  14. 2026EvoMU: Evolutionary Machine Unlearningcited by 0
  15. 2026MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Modelscited by 0
  16. 2026Say Something Else: Rethinking Contextual Privacy as Information Sufficiencycited by 0
  17. 2026Retain-Neutral Surrogates for Min-Max Unlearningcited by 0
  18. 2026Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearningcited by 0
  19. 2026AI Engram: In Search of Memory Traces in Artificial Intelligencecited by 0
  20. 2026SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vectorcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Leveraging Machine Unlearning for Cost-Efficient Preference Alignment
  2. 2023Large Language Model Unlearning
  3. 2025LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
  4. 2026CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization
  5. 2024Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
  6. 2025SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models
  7. 2026CAP: Controllable Alignment Prompting for Unlearning in LLMs
  8. 2024A Probabilistic Perspective on Unlearning and Alignment for Large Language Models