Aligning video multimodal models with a 350K-pair synthetic preference dataset, built via textual video descriptions, lifts GPT-4o-judged safety rates on a new video benchmark by up to 42 percentage points.
Safeinfer: Context adaptive decoding time safety alignment for large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SafeVid: Toward Safety Aligned Video Large Multimodal Models
Aligning video multimodal models with a 350K-pair synthetic preference dataset, built via textual video descriptions, lifts GPT-4o-judged safety rates on a new video benchmark by up to 42 percentage points.