Rethinking Post-Unlearning Behavior of Large Vision-Language Models

ACL ARR 2025 July Submission1331 Authors

Abstract: Machine unlearning is used to mitigate the privacy risks of Large Vision-Language Models (LVLMs) arising from training on large-scale web data. However, existing unlearning methods often fail to carefully select substitute outputs for forget targets, resulting in Unlearning Aftermaths—undesirable behaviors such as degenerate, hallucinated, or excessively refused responses. We highlight that, especially for generative LVLMs, it is crucial to consider the quality and informativeness of post-unlearning 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.

Paper Type: Short

Research Area: NLP Applications

Research Area Keywords: multimodal applications, security/privacy, NLP for social good

Contribution Types: NLP engineering experiment

Languages Studied: English

Previous URL: https://openreview.net/forum?id=6FlnTZ3jFB

Reassignment Request Area Chair: Yes, I want a different area chair for our submission

Reassignment Request Reviewers: Yes, I want a different set of reviewers

Justification For Not Keeping Action Editor Or Reviewers: The previous reviewer was unable to properly engage in the review discussion, as they did not clearly understand our mathematical formulations.

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: Yes

A2 Elaboration: in Ethics Statements section.

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: Section 4

B2 Discuss The License For Artifacts: N/A

B3 Artifact Use Consistent With Intended Use: N/A

B4 Data Contains Personally Identifying Info Or Offensive Content: Yes

B4 Elaboration: Section 4

B5 Documentation Of Artifacts: N/A

B5 Elaboration: N/A

B6 Statistics For Data: Yes

B6 Elaboration: Section 4

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Appendix C

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Appendix C

C3 Descriptive Statistics: Yes

C3 Elaboration: Section 4

C4 Parameters For Packages: Yes

C4 Elaboration: Section 4

D Human Subjects Including Annotators: Yes

D1 Instructions Given To Participants: N/A

D2 Recruitment And Payment: N/A

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: No

E1 Information About Use Of Ai Assistants: N/A

Author Submission Checklist: yes

Submission Number: 1331