Machine Unlearning Evaluation

Overview

Machine unlearning evaluation asks whether a model has genuinely lost the influence of specified training examples, facts, or users—not merely stopped producing them on familiar prompts. Common approaches compare behavior and utility with retrained models, measure membership or extraction risk, probe hidden representations, and test recovery through adversarial queries, fine-tuning, or sequential updates. Benchmarks span classifiers, language and vision-language models, generative systems, and agents, with checks for collateral damage to related knowledge and retained capabilities. A central tension remains: behavioral tests are practical but can miss recoverable information, while stronger audits may require costly reference models or risk exposing private data themselves.

Latest papers

CardsList

115 papers13 papers in the last four weeks, down 35% on the four weeks before. 0.1% of all new papers.

  1. Counterfactual Feature Steering for Adjacency-Preserving Identity Unlearning

    Nov 16, 2026FNU Shivam, Layth Sliman, Ramana Reddy +3Diffusion Model UnlearningMachine Unlearning

  2. Unlearning at Speed: Rapid Activation Dampening for Efficient Machine Unlearning in Real-World Face Recognition

    Nov 8, 2026Rouqaiah Al-Refai, Leo Scheubel, Philipp TerhörstMachine UnlearningFace Recognition

  3. DISCERN: Distributional Synthetic Replay for Retain-Free Incremental Machine Unlearning

    Nov 5, 2026Nicolás Segura-Kunsagi, Juan Luis Suárez-Díaz, Iván Sevillano-García +1Machine UnlearningGenerative Replay

  4. Do unlearning algorithms learn the right features?

    Nov 4, 2026Polina Dolgova, Amartya Sanyal, Sebastian U. StichMachine UnlearningMachine Unlearning Evaluation

  5. Auditable Unlearning for LLMs

    Nov 4, 2026Piyush Tiwary, Anushka Srivastava, Prathosh A. PMachine UnlearningLLM Unlearning

  6. Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds

    Nov 3, 2026Yaxin Xiao, Yulin Jin, Li Tang +4Machine UnlearningMachine Unlearning Evaluation

  7. Is Forgetting Unified? Exploring Concept Unlearning in Unified Multimodal Models

    Nov 3, 2026Zhongkai Xue, Junkai Chen, Mingcong Lei +7Concept ErasureUnified Multimodal Models

  8. Forget What Comes Next: LLM Unlearning via Statistical Independence

    Nov 2, 2026Andrii Shkabrii, Claudia Plant, Martin PawelczykHilbert-Schmidt Independence CriterionLLM Unlearning

  9. Loss is Not Behavior: A Unified Output-Space Analysis of Gradient-Based Machine Unlearning

    Oct 28, 2026Xingjian Zhao, Mohammad Mohammadi Amiri, Malik Magdon-IsmailMachine UnlearningMachine Unlearning Evaluation

  10. DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas

    Oct 28, 2026Tiantong Wu, Wei Yang Bryan LimMachine UnlearningMachine Unlearning Evaluation

  11. Risk-Aware Output Control Should be the Focus of Machine Unlearning

    Oct 26, 2026Yahya Alkhatib, Yuyang Xiao, Wee Peng TayMachine UnlearningMachine Unlearning Evaluation

  12. Approximate Unlearning in Prototype-based-classifiers

    Oct 25, 2026Sreejita Ghosh, Mohammad MohammadiMachine UnlearningMachine Unlearning Evaluation

  13. Does Unlearning Survive Collaboration? Robust Unlearning for Shared-Model LLM Teams

    Oct 19, 2026Hengsong Liu, Liangyu Teng, Jingnan Cai +5LLM UnlearningMachine Unlearning Evaluation

  14. Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods

    Oct 15, 2026Andrea D'Angelo, Francesco Gullo, Davide Mottin +2Graph UnlearningMachine Unlearning

  15. Behavioral Forgetting Is Not Privacy in Machine Unlearning

    Oct 15, 2026Tyler Lizzo, Larry HeckMachine UnlearningLLM Unlearning

  16. Not All Change Is Damage: Update-Matched Unlearning for Large Language Models

    Oct 15, 2026Jie Li, Youming Tao, Bowei He +1Machine UnlearningLLM Unlearning

  17. Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs

    Oct 14, 2026Oscar Chew, Po-Yi Lu, Yi-Jie Cheng +4MLLM UnlearningMachine Unlearning

  18. RA2^2: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning

    Oct 14, 2026Zinan Ling, Yang Xiao, Ruimeng Ye +2Machine UnlearningLLM Unlearning

  19. Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents

    Oct 13, 2026Bofan Xie, Chaokun Wang, Guanchen Ge +4LLM Agent MemoryMemory Agent Benchmarks

  20. Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents

    Oct 13, 2026Junkai Lin, Ge Xu, Zheng Xu +2Machine UnlearningLLM Unlearning

  21. Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning

    Oct 10, 2026Haodong Chen, Shengtao Wen, Dong Liang +2MLLM UnlearningRefusal Behavior in Language Models

  22. Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning

    Oct 8, 2026Xunlei Chen, Qinghui Gong, Jingkun Xue +3Machine UnlearningLLM Unlearning

  23. Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning

    Oct 7, 2026Junkai Chen, Yuhao He, Qianshan Wei +19MLLM UnlearningMachine Unlearning Evaluation

  24. Exact Unlearning via Quantized Sufficient Statistics

    Oct 5, 2026Ami Tavory, Shripad Gade, Tal Sarig +2Machine UnlearningMachine Unlearning Evaluation

  25. Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models

    Oct 4, 2026Kaiyuan Deng, Yuchen Li, Yang Xiao +3Diffusion Model UnlearningConcept Erasure

  26. From Mathematical to Executable Certificates for Machine Unlearning

    Oct 1, 2026Ziyu Zhao, Xinyu Wang, Xiaowen Chang +1Machine UnlearningMachine Unlearning Evaluation

  27. Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it

    Sep 29, 2026Hadi Reisizadeh, Jiajun Ruan, Sijia Liu +1Machine UnlearningLLM Unlearning

  28. Bounding Retraining Equivalence and the Deletion Floor in Materials Machine Unlearning

    Sep 28, 2026Can Polat, Mustafa Kurban, Erchin Serpedin +1Machine UnlearningMachine Unlearning Evaluation