Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations. To evaluate unlearning effectiveness in multimodal large language models (MLLMs), prior works fine-tune models on fictitious identities, simulating unlearning requests on subsets of these IDs, which are typically uniformly distributed. However, in realistic scenarios, people from different demographic groups may request to be unlearned at different frequencies, potentially altering the model's internal beliefs for these groups and leading to biased behaviors. To fill th
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%AI is more likely than humans to form biases when hiring →
- LinkedLinked via arxiv author · 85%Lorenzo Orsingher →
“Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning”
- LinkedLinked via arxiv author · 85%Thomas De Min →
“Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning”
- LinkedLinked via arxiv author · 85%Massimiliano Mancini →
“Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning”
- LinkedLinked via arxiv author · 85%Davide Talon →
“Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning”
- LinkedLinked via arxiv author · 85%Elisa Ricci →
“Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning”