Knowledge holes, severe response degradation on benign inputs that share patterns with forgotten content, are shown to exist in unlearned multimodal LLMs and are partially repaired by SPAR on LLaVA-1.5-7B.
CoRR , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models
Knowledge holes, severe response degradation on benign inputs that share patterns with forgotten content, are shown to exist in unlearned multimodal LLMs and are partially repaired by SPAR on LLaVA-1.5-7B.