Lune

ACL Findings2026

Rethinking Post-Unlearning Behavior of Large Vision-Language Models

Minsung Kim, Nakyeong Yang, Kyomin Jung

Abstract

Large Vision-Language Models (LVLMs) can recognize individuals in images and disclose sensitive personal information about them, raising critical privacy concerns. Machine unlearning aims to remove such knowledge from the model. However, existing methods rarely prescribe what the model should output in place of the forgotten content, leading to Unlearning Aftermaths: degenerate, hallucinated, or excessively refused responses. We argue that, especially for generative LVLMs, it is crucial to consider the quality and informativeness of postunlearning responses rather than relying solely on naive suppression. To address this, we introduce a new unlearning task for LVLMs that requires models to provide privacy-preserving yet informative and visually grounded responses. We also propose PUBG, a novel unlearning method that explicitly guides post-unlearning behavior toward a desirable output distribution. Experiments show that, while existing methods suffer from Unlearning Aftermaths despite successfully preventing privacy violations, PUBG effectively mitigates these issues, generating visually grounded and informative responses without privacy leakage for forgotten targets.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark cites Visual Instruction Tuning
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on14

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
  3. CLIPScore: A Reference-free Evaluation Metric for Image CaptioningJack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras et al.EMNLP 2021 · 937 citations
  4. Large Language Model UnlearningYuanshun Yao, Xiaojun Xu, Yang LiuNeurIPS 2024 · 365 citations
  5. MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language BenchmarkDongping Chen, Ruoxi Chen, Shilin Zhang, Yaochen Wang et al.ICML 2024 · 345 citations

Related papers

  1. Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model OutputsYiwei Chen, Soumyadeep Pal, Yimeng Zhang, Qing Qu et al.ICLR 2026 · 15 citations
  2. AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language ModelsHaokun Chen, Jianing Li, Yao Zhang, Jinhe Bi et al.AAAI 2026
  3. Decoding-Unlearning: Fact Forgetting via Entropy-Guided InferenceJingwen Pu, Mingjun Shi, Xinrui Ren, Yizhe Wang et al.ACL 2026
  4. Knowledge Unlearning for Mitigating Privacy Risks in Language ModelsJoel Jang, Dongkeun Yoon, Sohee Yang, Sungmin Cha et al.ACL 2023 · 48 citations
  5. Towards Robust Evaluation of Unlearning in LLMs via Data TransformationsAbhinav Joshi, Shaswati Saha, Divyaksh Shukla, Sriram Vema et al.EMNLP Findings 2024 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines