Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models

Documenti analoghi

• Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs
  di: Misra, Kanishka, et al.
  Pubblicazione: (2024)
• Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs
  di: Weissweiler, Leonie, et al.
  Pubblicazione: (2025)
• Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently
  di: Misra, Kanishka, et al.
  Pubblicazione: (2024)
• Models Can and Should Embrace the Communicative Nature of Human-Generated Math
  di: Boguraev, Sasha, et al.
  Pubblicazione: (2024)
• On Language Models' Sensitivity to Suspicious Coincidences
  di: Padmanabhan, Sriram, et al.
  Pubblicazione: (2025)