Towards Reproducible LLM Evaluation: Quantifying Uncertainty in LLM Benchmark Scores

Documenti analoghi

• Evaluating the Ability of Large Language Models to Reason about Cardinal Directions
  di: Cohn, Anthony G, et al.
  Pubblicazione: (2024)
• Evaluating the Ability of Large Language Models to Reason about Cardinal Directions, Revisited
  di: Cohn, Anthony G, et al.
  Pubblicazione: (2025)
• Can Large Language Models Reason about the Region Connection Calculus?
  di: Cohn, Anthony G, et al.
  Pubblicazione: (2024)
• QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi
  di: Cohn, Anthony G., et al.
  Pubblicazione: (2026)
• Exploring Spatial Representations in the Historical Lake District Texts with LLM-based Relation Extraction
  di: Haris, Erum, et al.
  Pubblicazione: (2024)