Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons

Documenti analoghi

• Derivational Morphology Reveals Analogical Generalization in Large Language Models
  di: Hofmann, Valentin, et al.
  Pubblicazione: (2024)
• Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena
  di: Weissweiler, Leonie, et al.
  Pubblicazione: (2024)
• Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs
  di: Mortensen, David R., et al.
  Pubblicazione: (2024)
• SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists
  di: Zhao, Raoyuan, et al.
  Pubblicazione: (2024)
• UCxn: Typologically Informed Annotation of Constructions Atop Universal Dependencies
  di: Weissweiler, Leonie, et al.
  Pubblicazione: (2024)