$\texttt{ModSCAN}$: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities

Ähnliche Einträge

• Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models
  von: Liu, Yugeng, et al.
  Veröffentlicht: (2023)
• Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
  von: Jiang, Yukun, et al.
  Veröffentlicht: (2025)
• Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
  von: Qu, Yiting, et al.
  Veröffentlicht: (2025)
• Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
  von: Chen, Zeyuan, et al.
  Veröffentlicht: (2026)
• Watermarking LLM-Generated Datasets in Downstream Tasks
  von: Liu, Yugeng, et al.
  Veröffentlicht: (2025)