EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models

Matthew Dahl, Varun Magesh, Mirac Suzgun, Daniel E Ho

Journal of Legal Analysis · 01.01.2024 · 16 (1) · 64-93

DOI: 10.1093/jla/laae003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Legal Analysis, online erschienen am 26.06.2024. Verfasst von Matthew Dahl und 3 weiteren Autor:innen. Die Arbeit wurde bisher 364-mal zitiert (Crossref) und nennt 121 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Do large language models (LLMs) know the law? LLMs are increasingly being used to augment legal practice, education, and research, yet their revolutionary potential is threatened by the presence of “hallucinations”—textual output that is not consistent with legal facts. We present the first systematic evidence of these hallucinations in public-facing LLMs, documenting trends across jurisdictions, courts, time periods, and cases. Using OpenAI’s ChatGPT 4 and other public models, we show that LLMs hallucinate at least 58% of the time, struggle to predict their own hallucinations, and often uncritically accept users’ incorrect legal assumptions. We conclude by cautioning against the rapid and unsupervised integration of popular LLMs into legal tasks, and we develop a typology of legal hallucinations to guide future research in this area.

Zitieren

APA

Dahl, M., Magesh, V., Suzgun, M., & Ho, D. E. (2024). Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models. Journal of Legal Analysis, 16(1), 64-93. https://doi.org/10.1093/jla/laae003

Vancouver

Dahl M, Magesh V, Suzgun M, Ho DE. Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models. Journal of Legal Analysis. 2024;16(1):64-93. doi:10.1093/jla/laae003

BibTeX
@article{Dahl2024,
  author = {Dahl, Matthew and Magesh, Varun and Suzgun, Mirac and Ho, Daniel E},
  title = {Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models},
  journal = {Journal of Legal Analysis},
  year = {2024},
  volume = {16},
  number = {1},
  pages = {64--93},
  doi = {10.1093/jla/laae003}
}
Kostenlos starten →