{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:58:18Z","timestamp":1786125498620,"version":"3.56.0"},"reference-count":7,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T00:00:00Z","timestamp":1724976000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Queue"],"published-print":{"date-parts":[[2024,8,30]]},"abstract":"<jats:p>The findings in this experiment support the hypothesis that GPTs based on LLMs perform well on prompts that are more popular and have reached a general consensus yet struggle on controversial topics or topics with limited data. The variability in the applications's responses underscores that the models depend on the quantity and quality of their training data, paralleling the system of crowdsourcing that relies on diverse and credible contributions. Thus, while GPTs can serve as useful tools for many mundane tasks, their engagement with obscure and polarized topics should be interpreted with caution. LLMs' reliance on probabilistic models to produce statements about the world ties their accuracy closely to the breadth and quality of the data they're given.<\/jats:p>","DOI":"10.1145\/3688007","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T15:28:07Z","timestamp":1725895687000},"page":"19-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":27,"title":["GPTs and Hallucination"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0852-5390","authenticated-orcid":false,"given":"Jim","family":"Waldo","sequence":"first","affiliation":[{"name":"Harvard University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4410-5204","authenticated-orcid":false,"given":"Soline","family":"Boussard","sequence":"additional","affiliation":[{"name":"Harvard University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"How to Do Things with Words","author":"Austin J. L.","unstructured":"Austin, J. L. 1962. How to Do Things with Words. Oxford University Press."},{"key":"e_1_2_1_2_1","volume-title":"editor","author":"Bacon F.","year":"1902","unstructured":"Bacon, F. Novum Organum. Joseph Devey, M.A., editor. New York: P.F. Collier, 1902."},{"key":"e_1_2_1_3_1","volume-title":"Meditations on First Philosophy (M. Moriarty, translator)","author":"Descartes R.","unstructured":"Descartes, R. 2008. Meditations on First Philosophy (M. Moriarty, translator). Oxford University Press."},{"key":"e_1_2_1_4_1","volume-title":"The Structure of Scientific Revolutions","author":"Kuhn T. S.","unstructured":"Kuhn, T. S. 1962. The Structure of Scientific Revolutions. University of Chicago Press."},{"key":"e_1_2_1_5_1","first-page":"67","article-title":"General semantics","author":"Lewis D.","year":"1970","unstructured":"Lewis, D. 1970. General semantics. Synthese 22 (1\/2), Semantics of Natural Language II,18?67. Springer Nature; https:\/\/www.jstor.org\/stable\/20114749.","journal-title":"Synthese 22 (1\/2), Semantics of Natural Language"},{"key":"e_1_2_1_6_1","series-title":"May 27","volume-title":"Here's what happens when your lawyer uses ChatGPT. New York Times","author":"Weiser B.","year":"2023","unstructured":"Weiser, B. 2023. Here's what happens when your lawyer uses ChatGPT. New York Times (May 27); https:\/\/www.nytimes.com\/2023\/05\/27\/nyregion\/avianca-airline-lawsuit-chatgpt.html."},{"key":"e_1_2_1_7_1","unstructured":"Wittgenstein L. 1953. Philosophical Investigations 1 (section 43). G.E.M. Anscombe editor. Wiley-Blackwell."}],"container-title":["Queue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688007","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3688007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:55Z","timestamp":1750291555000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3688007"}},"subtitle":["Why do large language models hallucinate?"],"short-title":[],"issued":{"date-parts":[[2024,8,30]]},"references-count":7,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8,30]]}},"alternative-id":["10.1145\/3688007"],"URL":"https:\/\/doi.org\/10.1145\/3688007","relation":{},"ISSN":["1542-7730","1542-7749"],"issn-type":[{"value":"1542-7730","type":"print"},{"value":"1542-7749","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,30]]},"assertion":[{"value":"2024-09-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}