RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs

Documenti analoghi

• Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions
  di: Testoni, Alberto, et al.
  Pubblicazione: (2024)
• Naming, Describing, and Quantifying Visual Objects in Humans and LLMs
  di: Testoni, Alberto, et al.
  Pubblicazione: (2024)
• It Depends: Resolving Referential Ambiguity in Minimal Contexts with Commonsense Knowledge
  di: Ellinger, Lukas, et al.
  Pubblicazione: (2025)
• Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain
  di: Mazzaccara, Davide, et al.
  Pubblicazione: (2024)
• Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?
  di: Baan, Joris, et al.
  Pubblicazione: (2024)