EUVIMEDEUVIMED entdecken
Crossref

Do large language models show decision heuristics similar to humans? A case study using GPT-3.5.

Gaurav Suri iD, Lily R Slater, Ali Ziaee, Morgan Nguyen

Journal of Experimental Psychology: General · 2024-04 · 153 (4) · 1066-1075

DOI: 10.1037/xge0001547 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Experimental Psychology: General, 2024-04. Verfasst von Gaurav Suri und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, San Francisco State University. Hauptthemen laut MEDLINE: Heuristics, Artificial Intelligence. Die Arbeit wurde bisher 77-mal zitiert (Crossref).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A Large Language Model (LLM) is an artificial intelligence system trained on vast amounts of natural language data, enabling it to generate human-like responses to written or spoken language input. Generative Pre-Trained Transformer (GPT)-3.5 is an example of an LLM that supports a conversational agent called ChatGPT. In this work, we used a series of novel prompts to determine whether ChatGPT shows heuristics and other context-sensitive responses. We also tested the same prompts on human participants. Across four studies, we found that ChatGPT was influenced by random anchors in making estimates (anchoring, Study 1); it judged the likelihood of two events occurring together to be higher than the likelihood of either event occurring alone, and it was influenced by anecdotal information (representativeness and availability heuristic, Study 2); it found an item to be more efficacious when its features were presented positively rather than negatively-even though both presentations contained statistically equivalent information (framing effect, Study 3); and it valued an owned item more than a newly found item even though the two items were objectively identical (endowment effect, Study 4). In each study, human participants showed similar effects. Heuristics and context-sensitive responses in humans are thought to be driven by cognitive and affective processes such as loss aversion and effort reduction. The fact that an LLM-which lacks these processes-also shows such responses invites consideration of the possibility that language is sufficiently rich to carry these effects and may play a role in generating these effects in humans. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HeuristicsArtificial IntelligenceHumansLanguageCommunicationAffect

Autor:innen und Institutionen

  • Department of Psychology, San Francisco State University.

ORCID-Profile: Gaurav Suri

Zitieren

APA

Suri, G., Slater, L. R., Ziaee, A., & Nguyen, M. (2024). Do large language models show decision heuristics similar to humans? A case study using GPT-3.5. Journal of Experimental Psychology: General, 153(4), 1066-1075. https://doi.org/10.1037/xge0001547

Vancouver

Suri G, Slater LR, Ziaee A, Nguyen M. Do large language models show decision heuristics similar to humans? A case study using GPT-3.5. Journal of Experimental Psychology: General. 2024;153(4):1066-1075. doi:10.1037/xge0001547

BibTeX
@article{Suri2024,
  author = {Suri, Gaurav and Slater, Lily R and Ziaee, Ali and Nguyen, Morgan},
  title = {Do large language models show decision heuristics similar to humans? A case study using GPT-3.5},
  journal = {Journal of Experimental Psychology: General},
  year = {2024},
  volume = {153},
  number = {4},
  pages = {1066--1075},
  doi = {10.1037/xge0001547}
}
Kostenlos starten →