FBHM benchmark exposes generalization failures in VLMs for hateful meme detection, addressed by LSV learnable steering vectors that deliver large gains from only 500 samples without harming source performance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection
FBHM benchmark exposes generalization failures in VLMs for hateful meme detection, addressed by LSV learnable steering vectors that deliver large gains from only 500 samples without harming source performance.