Lying to Win: Assessing LLM Deception through Human-AI Games and Parallel-World Probing

Documenti analoghi

• The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge
  di: Marioriyad, Arash, et al.
  Pubblicazione: (2025)
• The Judge Who Never Admits: Hidden Shortcuts in LLM-based Evaluation
  di: Marioriyad, Arash, et al.
  Pubblicazione: (2026)
• Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey
  di: Shahhosseini, Fatemeh, et al.
  Pubblicazione: (2025)
• Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models
  di: Rezaei, Parham, et al.
  Pubblicazione: (2025)
• Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models
  di: Marioriyad, Arash, et al.
  Pubblicazione: (2024)