STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions

Documenti analoghi

• The Dog the Cat Chased Stumped the Model: Measuring When Language Models Abandon Structure for Shortcuts
  di: Madhusudan, Sangmitra, et al.
  Pubblicazione: (2025)
• Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition
  di: McDonald, Tyler, et al.
  Pubblicazione: (2025)
• MirrorStories: Reflecting Diversity through Personalized Narrative Generation with Large Language Models
  di: Yunusov, Sarfaroz, et al.
  Pubblicazione: (2024)
• Fine-Tuned LLMs are "Time Capsules" for Tracking Societal Bias Through Books
  di: Madhusudan, Sangmitra, et al.
  Pubblicazione: (2025)
• NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers
  di: Lopez, Angel Yahir Loredo, et al.
  Pubblicazione: (2024)