VISE is the first benchmark for sycophancy in Video-LLMs, with two training-free mitigation strategies based on key-frame selection and internal representation steering.
Benchmarking trustworthiness of multi- modal large language models: A comprehensive study
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
BadRDM is a backdoor attack on retrieval-augmented diffusion models that poisons the retrieval database with toxicity surrogates and uses multimodal contrastive learning to force toxic generations from text triggers while preserving benign performance.
citing papers explorer
-
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
VISE is the first benchmark for sycophancy in Video-LLMs, with two training-free mitigation strategies based on key-frame selection and internal representation steering.
-
Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models
BadRDM is a backdoor attack on retrieval-augmented diffusion models that poisons the retrieval database with toxicity surrogates and uses multimodal contrastive learning to force toxic generations from text triggers while preserving benign performance.
- Investigating Adversarial Robustness of Multi-modal Large Language Models