Predictions from language models for multiple-choice tasks are not robust under variation of scoring methods

Documenti analoghi

• Bayesian Statistical Modeling with Predictors from LLMs
  di: Franke, Michael, et al.
  Pubblicazione: (2024)
• Cognitive Modeling with Scaffolded LLMs: A Case Study of Referential Expression Generation
  di: Tsvilodub, Polina, et al.
  Pubblicazione: (2024)
• Integrating Neural and Symbolic Components in a Model of Pragmatic Question-Answering
  di: Tsvilodub, Polina, et al.
  Pubblicazione: (2025)
• Experimental Pragmatics with Machines: Testing LLM Predictions for the Inferences of Plain and Embedded Disjunctions
  di: Tsvilodub, Polina, et al.
  Pubblicazione: (2024)
• Act or Clarify? Modeling Sensitivity to Uncertainty and Cost in Communication
  di: Tsvilodub, Polina, et al.
  Pubblicazione: (2026)