EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

The Pitfalls of Defining Hallucination

Kees van Deemter

Computational Linguistics · 01.06.2024 · 50 (2) · 807-816

DOI: 10.1162/coli_a_00509 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Linguistics, online erschienen am 01.06.2024. Verfasst von Kees van Deemter. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite impressive advances in Natural Language Generation (NLG) and Large Language Models (LLMs), researchers are still unclear about important aspects of NLG evaluation. To substantiate this claim, I examine current classifications of hallucination and omission in data-text NLG, and I propose a logic-based synthesis of these classfications. I conclude by highlighting some remaining limitations of all current thinking about hallucination and by discussing implications for LLMs.

Zitieren

APA

Deemter, K. V. (2024). The Pitfalls of Defining Hallucination. Computational Linguistics, 50(2), 807-816. https://doi.org/10.1162/coli_a_00509

Vancouver

Deemter KV. The Pitfalls of Defining Hallucination. Computational Linguistics. 2024;50(2):807-816. doi:10.1162/coli_a_00509

BibTeX
@article{Deemter2024,
  author = {Deemter, Kees van},
  title = {The Pitfalls of Defining Hallucination},
  journal = {Computational Linguistics},
  year = {2024},
  volume = {50},
  number = {2},
  pages = {807--816},
  doi = {10.1162/coli_a_00509}
}
Kostenlos starten →