{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:35:24Z","timestamp":1780929324841,"version":"3.54.1"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T00:00:00Z","timestamp":1684886400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Backgrounds<\/jats:title><jats:p>The field of Artificial Intelligence (AI) has seen a major shift in recent years due to the development of new Machine Learning (ML) models such as Generative Pre-trained Transformer (GPT). GPT has achieved previously unheard-of levels of accuracy in most computerized language processing tasks and their chat-based variations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Aim<\/jats:title><jats:p>The aim of this study was to investigate the problem-solving abilities of ChatGPT using two sets of verbal insight problems, with a known performance level established by a sample of human participants.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>A total of 30 problems labeled as \u201c<jats:italic>practice problems<\/jats:italic>\u201d and \u201c<jats:italic>transfer problems<\/jats:italic>\u201d were administered to ChatGPT. ChatGPT's answers received a score of \u201c0\u201d for each incorrectly answered problem and a score of \u201c1\u201d for each correct response. The highest possible score for both the <jats:italic>practice<\/jats:italic> and <jats:italic>transfer<\/jats:italic> problems was 15 out of 15. The solution rate for each problem (based on a sample of 20 subjects) was used to assess and compare the performance of ChatGPT with that of human subjects.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The study highlighted that ChatGPT can be trained in out-of-the-box thinking and demonstrated potential in solving verbal insight problems. The global performance of ChatGPT equalled the most probable outcome for the human sample in both <jats:italic>practice problems<\/jats:italic> and <jats:italic>transfer problems<\/jats:italic> as well as upon their combination. Additionally, ChatGPT answer combinations were among the 5% of most probable outcomes for the human sample both when considering <jats:italic>practice problems<\/jats:italic> and pooled problem sets. These findings demonstrate that ChatGPT performance on both set of problems was in line with the mean rate of success of human subjects, indicating that it performed reasonably well.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The use of transformer architecture and self-attention in ChatGPT may have helped to prioritize inputs while predicting, contributing to its potential in verbal insight problem-solving. ChatGPT has shown potential in solving insight problems, thus highlighting the importance of incorporating AI into psychological research. However, it is acknowledged that there are still open challenges. Indeed, further research is required to fully understand AI's capabilities and limitations in verbal problem-solving.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2023.1199350","type":"journal-article","created":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T05:14:33Z","timestamp":1684905273000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":140,"title":["Human-like problem-solving abilities in large language models using ChatGPT"],"prefix":"10.3389","volume":"6","author":[{"given":"Graziella","family":"Orr\u00f9","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Piarulli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ciro","family":"Conversano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angelo","family":"Gemignani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,5,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1002\/j.2162-6057.2000.tb01201.x","article-title":"Promoting insightful problem solving","volume":"34","author":"Ansburg","year":"2000","journal-title":"J. Creat. Behav."},{"key":"B2","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv preprint arXiv:1409.0473"},{"key":"B3","first-page":"S109","article-title":"The inflammatory hypothesis of mood spectrum broadened to fibromyalgia and chronic fatigue syndrome","volume":"33","author":"Dell'Osso","year":"2015","journal-title":"Clin. Exp. Rheumatol."},{"key":"B4","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e0265803","DOI":"10.1371\/journal.pone.0265803","article-title":"Alternate fluency in Parkinson's disease: a machine learning analysis","volume":"17","author":"Ferrucci","year":"2022","journal-title":"PLoS ONE"},{"key":"B6","volume-title":"The Principles of Psychology Volume II By William James","author":"James","year":"1890"},{"key":"B7","volume-title":"The Principles of Psychology","author":"James","year":"2007"},{"key":"B8","volume-title":"Thinking, Fast and Slow","author":"Kahneman","year":"2011"},{"key":"B9","article-title":"A simple way to initialize recurrent networks of rectified linear units","author":"Le","year":"2015","journal-title":"arXiv preprint arXiv:1504.00941"},{"key":"B10","first-page":"5457","article-title":"\u201cIndependently recurrent neural network (indrnn): building a longer and deeper rnn,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2018"},{"key":"B11","doi-asserted-by":"crossref","unstructured":"LoconteR.\n            Orr\u00f9G.\n            TribastoneM.\n            PietriniP.\n            SartoriG.\n          Challenging ChatGPT ' Intelligence' with Human Tools: A Neuropsychological Investigation on Prefrontal Functioning of a Large Language Model2023","DOI":"10.2139\/ssrn.4377371"},{"key":"B12","volume-title":"Thinking, Problem Solving, Cognition","author":"Mayer","year":"1992"},{"key":"B13","first-page":"287","article-title":"\u201cProblem solving,\u201d","volume-title":"Handbook of Educational Psychology","author":"Mayer","year":"2006"},{"key":"B14","doi-asserted-by":"publisher","first-page":"389","DOI":"10.3389\/fpsyt.2019.00389","article-title":"Introducing machine learning to detect personality faking-good in a male sample: a new model based on Minnesota multiphasic personality inventory-2 restructured form scales and reaction times","volume":"10","author":"Mazza","year":"2019","journal-title":"Front. Psychiatry"},{"key":"B15","volume-title":"Human Problem Solving (Vol. 104, No. 9)","author":"Newell","year":"1972"},{"key":"B16","doi-asserted-by":"publisher","first-page":"66","DOI":"10.2174\/2666082217666210913101627","article-title":"A brief overview on the contribution of machine learning in systems neuroscience","volume":"17","author":"Orr\u00f9","year":"2021","journal-title":"Curr. Psychiatry Res. Rev. Formerly Curr. Psychiatry Rev."},{"key":"B17","doi-asserted-by":"publisher","first-page":"319","DOI":"10.3389\/fmed.2019.00319","article-title":"Machine learning increases diagnosticity in psychometric evaluation of alexithymia in fibromyalgia","volume":"6","author":"Orr\u00f9","year":"","journal-title":"Front. Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"2970","DOI":"10.3389\/fpsyg.2019.02970","article-title":"Machine learning in psychometrics and psychological research","volume":"10","author":"Orr\u00f9","year":"","journal-title":"Front. Psychol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1016\/j.neubiorev.2012.01.004","article-title":"Using support vector machine to identify imaging biomarkers of neurological and psychiatric disease: a critical review","volume":"36","author":"Orr\u00f9","year":"2012","journal-title":"Neurosci. Biobehav. Rev."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.3389\/fpsyg.2019.01650","article-title":"Malingering detection of cognitive impairment with the B test is boosted using machine learning","volume":"10","author":"Pace","year":"2019","journal-title":"Front. Psychol."},{"key":"B21","doi-asserted-by":"crossref","first-page":"2249","DOI":"10.18653\/v1\/D16-1244","article-title":"\u201cA decomposable attention model,\u201d","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Parikh","year":"2016"},{"key":"B22","first-page":"433","article-title":"\u201cLearning accurate, compact, and interpretable tree annotation,\u201d","volume-title":"Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the ACL","author":"Petrov","year":"2016"},{"key":"B23","volume-title":"How to Solve It: A New Aspect of Mathematical Method (No. 246)","author":"Polya","year":"2004"},{"key":"B24","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1007\/978-3-319-67092-8_21","article-title":"\u201cDetection of malingering in psychic damage ascertainment,\u201d","volume-title":"P5 Medicine and Justice: Innovation, Unitariness and Evidence","author":"Sartori","year":"2017"},{"key":"B25","first-page":"1","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"B26","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"B27","volume-title":"The Art of Thought (Vol. 10)","author":"Wallas","year":"1926"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1199350\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T05:14:53Z","timestamp":1684905293000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1199350\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,24]]},"references-count":27,"alternative-id":["10.3389\/frai.2023.1199350"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1199350","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,24]]},"article-number":"1199350"}}