The paper benchmarks sycophancy in medical VLMs using hierarchical VQA templates and proposes VIPER to filter non-evidence social cues, reducing sycophancy while preserving interpretability.
Using social and behavioural science to support covid-19 pandemic response.Nature human behaviour, 4(5):460–471
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Benchmarking and Mitigating Sycophancy in Medical Vision Language Models
The paper benchmarks sycophancy in medical VLMs using hierarchical VQA templates and proposes VIPER to filter non-evidence social cues, reducing sycophancy while preserving interpretability.