Tesis doctoralsDepartament d'Estudis Anglesos i Alemanys

Large Language Models: Language abilities and limitations

  • Datos identificativos

    Identificador:  TDX:4499
    Autores:  Dentella, Vittoria
    Resumen:
    Large Language Models (LLMs) are recruited in applications that generate strings of text that closely resemble natural language. On this basis, LLMs have been invested with human-like capabilities such as understanding, reasoning, and intelligence. Additionally, their adoption as cognitive theories capable of explaining language processing in humans is increasingly called for. However, a closer look reveals that the language outputs of LLMs are replete with inconsistencies and content no neurotypical human would produce, casting doubt on the human-likeness of the linguistic knowledge they encode. In this thesis, (1) an outline is drawn of the knowledge over morphosyntax, semantics and pragmatics that LLMs are attributed with; (2) experimental evidence is provided that similarities between LLMs’ outputs and natural language hold only superficially and thus, the two are not qualitatively comparable; and (3) a discussion is offered on the choice of methods used to evaluate the linguistic abilities of LLMs.
  • Otros:

    Editor: Universitat Rovira i Virgili
    Fecha: 2026-09-20T02:00:00Z, 2024-09-20, 2024-11-14T11:40:28Z
    Identificador: http://hdl.handle.net/10803/692537
    Departamento/Instituto: Departament d'Estudis Anglesos i Alemanys, Universitat Rovira i Virgili.
    Idioma: eng
    Autor: Dentella, Vittoria
    Director: Oltra Massuet, Maria Isabel, Leivada, Evangelia
    Fuente: TDX (Tesis Doctorals en Xarxa)
    Formato: application/pdf, 118 p.
  • Palabras clave:

    morphosyntax
    natural language
    large language models
    lenguaje natural
    modelos de lenguaje masivo
    morfosintaxi
    llenguatge natural
    models de llenguatge massiu
    159.9
    Arts i humanitats
  • Documentos:

  • Cerca a google

    Search to google scholar