{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T01:17:01Z","timestamp":1792804621096,"version":"4.5.0"},"reference-count":51,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T00:00:00Z","timestamp":1706486400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Autism Research"],"published-print":{"date-parts":[[2024,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Given the increasing role of artificial intelligence (AI) in many decision\u2010making processes, we investigate the presence of AI bias towards terms related to a range of neurodivergent conditions, including autism, ADHD, schizophrenia, and obsessive\u2010compulsive disorder (OCD). We use 11 different language model encoders to test the degree to which words related to neurodiversity are associated with groups of words related to danger, disease, badness, and other negative concepts. For each group of words tested, we report the mean strength of association (Word Embedding Association Test [WEAT] score) averaged over all encoders and find generally high levels of bias. Additionally, we show that bias occurs even when testing words associated with autistic or neurodivergent strengths. For example, embedders had a negative average association between words related to autism and words related to honesty, despite honesty being considered a common strength of autistic individuals. Finally, we introduce a sentence similarity ratio test and demonstrate that many sentences describing types of disabilities, for example, \u201cI have autism\u201d or \u201cI have epilepsy,\u201d have even stronger negative associations than control sentences such as \u201cI am a bank robber.\u201d<\/jats:p>","DOI":"10.1002\/aur.3094","type":"journal-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T10:29:45Z","timestamp":1706524185000},"page":"234-248","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Prevalence of bias against neurodivergence\u2010related terms in artificial intelligence language models"],"prefix":"10.1002","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5687-2412","authenticated-orcid":false,"given":"Sam","family":"Brandsen","sequence":"first","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences Duke University  Durham North Carolina USA"},{"name":"Duke Center for Autism and Brain Development Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara","family":"Chandrasekhar","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences Duke University  Durham North Carolina USA"},{"name":"Duke Center for Autism and Brain Development Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lauren","family":"Franz","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences Duke University  Durham North Carolina USA"},{"name":"Duke Center for Autism and Brain Development Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordan","family":"Grapel","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences Duke University  Durham North Carolina USA"},{"name":"Duke Center for Autism and Brain Development Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geraldine","family":"Dawson","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences Duke University  Durham North Carolina USA"},{"name":"Duke Center for Autism and Brain Development Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Carlson","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering Duke University  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,1,29]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0277-9536(96)00065-2"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/13623613211057974"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18084272"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/0956797615595607"},{"key":"e_1_2_8_6_1","unstructured":"Bolukbasi T. Chang K. Zou J. Saligrama V. &Kalai A.(2016).Man is to computer programmer as woman is to homemaker? Debiasing Word Embeddings arXiv 1607.06520."},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1089\/aut.2020.0014"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph16234821"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aal4230"},{"key":"e_1_2_8_10_1","unstructured":"Dastin J.(2018 October 10).Amazon scraps secret AI recruiting tool that showed bias against women. Retrieved February 27 2023 fromhttps:\/\/www.reuters.com\/article\/us\u2010amazon\u2010com\u2010jobs\u2010automation\u2010insight\u2010idUSKCN1MK08G"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-056904"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10803-014-2194-7"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.01211"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10803-020-04556-7"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2021.645232"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/15532739.2019.1594484"},{"key":"e_1_2_8_17_1","unstructured":"Hugging Face. (2022a).Sentence\u2010transformers\/all\u2010minilm\u2010L6\u2010V2. Retrieved February 27 2023 fromhttps:\/\/huggingface.co\/sentence-transformers\/all-MiniLM-L6-v2"},{"key":"e_1_2_8_18_1","unstructured":"Hugging Face. (2022b).Sentence\u2010transformers\/multi\u2010qa\u2010mpnet\u2010base\u2010dot\u2010v1. Retrieved February 27 2023 fromhttps:\/\/huggingface.co\/sentence-transformers\/multi-qa-mpnet-base-dot-v1"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"Kaneko M. &Bollegala D.(2019).Gendeer\u2010preserving debiasing for pre\u2010trained word embeddings.Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. doi:10.18653\/v1\/p19\u20101160","DOI":"10.18653\/v1\/P19-1160"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44184-022-00002-x"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.895997"},{"key":"e_1_2_8_22_1","unstructured":"Mahoney M.(2011).About the test data. Retrieved February 28 2023 fromhttp:\/\/mattmahoney.net\/dc\/textdata"},{"key":"e_1_2_8_23_1","unstructured":"Mikolov T. Chen K. Corrado G. &Dean J.(2013).Efficient estimation of word representations in vector space. arXiv.https:\/\/doi.org\/10.48550\/ARXIV.1301.3781"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1177\/1042258719890986"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.5014\/ajot.2017.71s1-po3090"},{"key":"e_1_2_8_26_1","unstructured":"OpenAI. (2023a).Openai\/openai\u2010python: The openai python library provides convenient access to the openai API from applications written in the python language. Retrieved February 27 2023 fromhttps:\/\/github.com\/openai\/openai-python"},{"key":"e_1_2_8_27_1","unstructured":"OpenAI. (2023b).Language models are unsupervised multitask learners. Retrieved February 28 2023 fromhttps:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"Papakyriakopoulos O. Hegelich S. Serrano J. C. &Marco F.(2020).Bias in word embeddings.Proceedings of the 2020 Conference on Fairness Accountability and Transparency.https:\/\/doi.org\/10.1145\/3351095.3372843","DOI":"10.1145\/3351095.3372843"},{"key":"e_1_2_8_29_1","unstructured":"Parraga O. More M. Oliveira C. Gavenski N. Kupssinsk\u00fc L. Medronha A. Moura L. Sim\u00f5es G. &Barros R.(2022).Debiasing methods for fairer neural models in vision and language research: A survey. arXiv.https:\/\/doi.org\/10.48550\/ARXIV.2211.05617"},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"Pennington J. Socher R. &Manning C. D.(2014).GloVe: Global vectors for word representation. Retrieved February 27 2023 fromhttps:\/\/nlp.stanford.edu\/projects\/glove\/","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-020-00992-6"},{"key":"e_1_2_8_32_1","unstructured":"Radford A. Wu J. Child R. Luan D. Amodei D. & Sutskever I.(2019).Language Models are Unsupervised Multitask Learners.https:\/\/www.semanticscholar.org\/paper\/Language\u2010Models\u2010are\u2010Unsupervised\u2010Multitask\u2010Learners\u2010Radford\u2010Wu\/9405cc0d6169988371b2755e573cc28650d14dfe"},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"Rahman R.(2020).Robust and consistent estimation of word embedding for Bangla language by fine\u2010tuning word2vec model.2020 23rd International Conference on Computer and Information Technology(ICCIT).https:\/\/doi.org\/10.1109\/iccit51783.2020.9392738","DOI":"10.1109\/ICCIT51783.2020.9392738"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.3109\/09638288.2014.956814"},{"key":"e_1_2_8_35_1","doi-asserted-by":"crossref","unstructured":"Reimers N. &Gurevych I.(2019).Sentence\u2010bert: Sentence embeddings using Siamese Bert\u2010networks.Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP\u2010IJCNLP).https:\/\/doi.org\/10.18653\/v1\/d19-1410","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1089\/aut.2018.0035"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10912-010-9135-z"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep40700"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2006.08564"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/aur.2794"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.1b5c3b7b"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1352\/1934-9556-48.2.126"},{"key":"e_1_2_8_43_1","unstructured":"Sogancioglu G. &Kaya H.(2022).The effects of gender bias in word embeddings on depression prediction. arXiv.https:\/\/doi.org\/10.48550\/ARXIV.2212.07852"},{"key":"e_1_2_8_44_1","doi-asserted-by":"crossref","unstructured":"Speer R. Chin J. &Havasi C.(2016).ConceptNet 5.5: An open multilingual graph of general knowledge. arXiv.https:\/\/doi.org\/10.48550\/ARXIV.1612.03975","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_2_8_45_1","unstructured":"Speer R.(2017a July 5).ConceptNet 5.5.5 update. Retrieved February 27 2023 fromhttp:\/\/blog.conceptnet.io\/posts\/2017\/conceptnet-5-5-5-update\/"},{"key":"e_1_2_8_46_1","unstructured":"Speer R.(2017b April 24).Conceptnet numberbatch 17.04: Better less\u2010stereotyped word vectors. Retrieved February 27 2023 fromhttp:\/\/blog.conceptnet.io\/posts\/2017\/conceptnet-numberbatch-17-04-better-less-stereotyped-word-vectors\/"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.18061\/dsq.v31i3.1675"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1177\/13623613221130845"},{"key":"e_1_2_8_49_1","doi-asserted-by":"crossref","unstructured":"Verma S. &Rubin J.(2018).Fairness definitions explained. Proceedings of the International Workshop on Software Fairness.https:\/\/doi.org\/10.1145\/3194770.3194776","DOI":"10.1145\/3194770.3194776"},{"key":"e_1_2_8_50_1","doi-asserted-by":"publisher","DOI":"10.1093\/geront\/gnp107"},{"key":"e_1_2_8_51_1","doi-asserted-by":"crossref","unstructured":"Wolf T. Debut L. Sanh V. Chaumond J. Delangue C. Moi A. Cistac P. Rault T. Louf R. Funtowicz M. Davison J. Shleifer S. vonPlaten P. Ma C. Jernite Y. Plu J. Xu C. Le Scao T. Gugger S. \u2026Rush A.(2020 July 14).Huggingface's transformers: State\u2010of\u2010the\u2010art natural language processing. Retrieved February 27 2023 fromhttps:\/\/arxiv.org\/abs\/1910.03771","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_2_8_52_1","doi-asserted-by":"crossref","unstructured":"Wu Y. &Kelly R. M.(2020).Online dating meets artificial intelligence: How the perception of algorithmically generated profile text impacts attractiveness and trust.32nd Australian Conference on Human\u2010Computer Interaction.https:\/\/doi.org\/10.1145\/3441000.3441074","DOI":"10.1145\/3441000.3441074"}],"container-title":["Autism Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aur.3094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T08:21:14Z","timestamp":1708676474000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/aur.3094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,29]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["10.1002\/aur.3094"],"URL":"https:\/\/doi.org\/10.1002\/aur.3094","archive":["Portico"],"relation":{},"ISSN":["1939-3792","1939-3806"],"issn-type":[{"value":"1939-3792","type":"print"},{"value":"1939-3806","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,29]]},"assertion":[{"value":"2023-06-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-27","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-01-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}