PSA-VLM adds a safety classifier and prompt-rewriting gate to LLaVA-style vision-language models, reporting state-of-the-art average safety scores on RTVLM and large gains on politics, porn, and cyberbullying datasets.
Introducing our multimodal models, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PSA-VLM: Enhancing Vision-Language Model Safety through Progressive Concept-Bottleneck-Driven Alignment
PSA-VLM adds a safety classifier and prompt-rewriting gate to LLaVA-style vision-language models, reporting state-of-the-art average safety scores on RTVLM and large gains on politics, porn, and cyberbullying datasets.