Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models
Ranking
Overall
81
Content
100
Popularity
37
Observed public metrics from 1 member.
Merged summary
TL;DR - PAVA is a retain-free method for removing an individual’s identity information from multimodal large language models while preserving visual-language capabilities. It matters because it avoids reconstructing privacy-sensitive retain sets after deployment.
- Causal tracing, weight transplant, and Fisher overlap localize identity information primarily to early-to-mid decoder MLP layers.
- PAVA restricts updates to those layers to reduce disruption to shared visual-language processing.
- A visual-attribute anchor distills the model’s pre-unlearning, image-grounded answers using only forget-set images.
- On MLLMU-Bench and ReMem, PAVA achieves the strongest forget-retain trade-off among forget-set-only methods and remains competitive with retain-based baselines.
Sources (1)
Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - PAVA is a retain-free method for removing an individual’s identity information from multimodal large language models while preserving visual-language capabilities. It matters because it avoids reconstructing privacy-sensitive retain sets after deployment.
- Causal tracing, weight transplant, and Fisher overlap localize identity information primarily to early-to-mid decoder MLP layers.
- PAVA restricts updates to those layers to reduce disruption to shared visual-language processing.
- A visual-attribute anchor distills the model’s pre-unlearning, image-grounded answers using only forget-set images.
- On MLLMU-Bench and ReMem, PAVA achieves the strongest forget-retain trade-off among forget-set-only methods and remains competitive with retain-based baselines.