mlsanityData to 14 Oct 2026

Unified Parameter-Efficient Unlearning for LLMs

arXiv 2412.00383 ↗First posted 30 Nov 2024cs.AI cs.LGcited by 25

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

The advent of Large Language Models (LLMs) has revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks. Fine-tuning these models for specific domains, particularly through Parameter-Efficient Fine-Tuning (PEFT) strategies like LoRA, has become a prevalent practice due to its efficiency. However, this raises significant privacy and security concerns, as models may inadvertently retain and disseminate sensitive or undesirable information. To address these issues, we introduce a novel instance-wise unlearning framework, LLMEraser, which systematically categorizes unlearning tasks and applies precise parameter adjustments using influence functions. Unlike traditional unlearning techniques that are often limited in scope and require extensive retraining, LLMEraser is designed to handle a broad spectrum of unlearning tasks without compromising model performance. Extensive experiments on benchmark datasets demonstrate that LLMEraser excels in efficiently managing various unlearning scenarios while maintaining the overall integrity and efficacy of the models.

Key facts. Cited by 25 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 71 of its 99 references that are in the map. First posted on arXiv 30 Nov 2024.

Builds on

71 of 99 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Rethinking Machine Unlearning for Large Language Models13 Feb

Other references · 70

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  8. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  9. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  11. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  12. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
38 more
  1. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  2. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  3. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
  4. 2019Machine Unlearningcited by 1,061
  5. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 689
  6. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Modelscited by 437
  7. 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 384
  8. 2023Who's Harry Potter? Approximate Unlearning in LLMscited by 381
  9. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 371
  10. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 337
  11. 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 274
  12. 2023Towards Unbounded Machine Unlearningcited by 268
  13. 2020Influence Functions in Deep Learning Are Fragilecited by 252
  14. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 237
  15. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 236
  16. 2023Using an LLM to Help With Code Understandingcited by 228
  17. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
  18. 2023In-Context Unlearning: Language Models as Few Shot Unlearnerscited by 224
  19. 2023Unlearn What You Want to Forget: Efficient Unlearning for LLMscited by 215
  20. 2024When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Methodcited by 204
  21. 2024Towards Safer Large Language Models through Machine Unlearningcited by 139
  22. 2024LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuningcited by 136
  23. 2024Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloadscited by 121
  24. 2022Adam Can Converge Without Any Modification On Update Rulescited by 114
  25. 2024β-DPO: Direct Preference Optimization with Dynamic βcited by 90
  26. 2023ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testingcited by 88
  27. 2022Recommendation Unlearningcited by 80
  28. 2023LLM-Rec: Personalized Recommendation via Prompting Large Language Modelscited by 77
  29. 2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifierscited by 67
  30. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
  31. 2023GIF: A General Graph Unlearning Strategy via Influence Functioncited by 60
  32. 2024Understanding LLMs: A Comprehensive Overview from Training to Inferencecited by 59
  33. 2023LLaRA: Large Language-Recommendation Assistantcited by 56
  34. 2024Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledgecited by 51
  35. 2024Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learningcited by 51
  36. 2024Digital Forgetting in Large Language Models: A Survey of Unlearning Methodscited by 40
  37. 2022On the Effectiveness of Sampled Softmax Loss for Item Recommendationcited by 39
  38. 2022Privacy Adhering Machine Un-learning in NLPcited by 36

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 14.

25 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  2. 2025OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metricscited by 83
  3. 2025ReLearn: Unlearning via Learning for Large Language Modelscited by 22
  4. 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Languagecited by 21
  5. 2025GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detectioncited by 17
  6. 2025MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steeringcited by 10
  7. 2026Attention Smoothing Is All You Need For Unlearningcited by 7
  8. 2025Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillationcited by 4
  9. 2026Reinforcement Unlearning via Group Relative Policy Optimizationcited by 4
  10. 2025Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimizationcited by 2
  11. 2025Reveal and Release: Iterative LLM Unlearning with Self-generated Datacited by 2
  12. 2025Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusionscited by 2
13 more
  1. 2026Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilitiescited by 1
  2. 2025FiCABU: A Fisher-Based, Context-Adaptive Machine Unlearning Processor for Edge AIcited by 0
  3. 2026Unlearning in LLMs: Methods, Evaluation, and Open Challengescited by 0
  4. 2026Retain-Neutral Surrogates for Min-Max Unlearningcited by 0
  5. 2026Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoningcited by 0
  6. 2026Goal-Conditioned Supervised Learning for LLM Fine-Tuningcited by 0
  7. 2026Interference-Aware Multi-Task Unlearningcited by 0
  8. 2026Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearningcited by 0
  9. 2026MPSelectTune: Prompt-type Selection for Fine-tuning improves Concept Unlearning in LLMscited by 0
  10. 2026The Safeguard Worked. Is the LLM System Safer?cited by 0
  11. 2026Storage Is Not Strategy: State-Conditioned Support Control for LLM Unlearningcited by 0
  12. 2026Faithful Dual-constrained Erasure for Robust LLM Safety Alignmentcited by 0
  13. 2026CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
  2. 2023Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges
  3. 2024Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
  4. 2025UniErase: Towards Balanced and Precise Unlearning in Language Models
  5. 2025LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples
  6. 2026Explainable LLM Unlearning Through Reasoning
  7. 2025A Survey on Unlearning in Large Language Models
  8. 2024Machine Unlearning of Pre-trained Large Language Models