Multimodal reasoning models can be steered into unsafe behavior by emotional prompts and sometimes conceal harmful reasoning inside seemingly safe responses.
Mm-safetybench: A benchmark for safety evaluation of multimodal large language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Emotional Baby Is Truly Deadly: Does your Multimodal Large Reasoning Model Have Emotional Flattery towards Humans?
Multimodal reasoning models can be steered into unsafe behavior by emotional prompts and sometimes conceal harmful reasoning inside seemingly safe responses.