{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T12:08:05Z","timestamp":1774008485124,"version":"3.50.1"},"reference-count":26,"publisher":"Association for Computing Machinery (ACM)","issue":"9","license":[{"start":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T00:00:00Z","timestamp":1724630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2024,9]]},"abstract":"<jats:p>The natural language capabilities demonstrated by large language models (LLMs) highlight an opportunity for new writing support tools that address the varied needs of people with dyslexia. We present LaMPost, a prototype email editor that draws upon our understanding of these needs to motivate AI-powered writing features, such as outlining main ideas, generating a subject line, suggesting changes, and rewriting a selection. We evaluated LaMPost with 19 adults with dyslexia, identifying promising routes for further exploration (such as the popular \u201crewrite\u201d and \u201csubject line\u201d features), while also finding that the current generation of LLMs may not yet meet the accuracy and quality thresholds to be useful for writers with dyslexia. In addition, knowledge of the AI did not alter participants\u2019 perception of the system nor their feelings of autonomy, expression, and self-efficacy when writing emails. Our findings provide insight into the benefits and drawbacks of LLMs as writing support for adults with dyslexia, and they offer a foundation to build upon in future research.<\/jats:p>","DOI":"10.1145\/3626952","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:21:55Z","timestamp":1723051315000},"page":"80-89","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["LaMPost: AI Writing Assistance for Adults with Dyslexia Using Large Language Models"],"prefix":"10.1145","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7381-1942","authenticated-orcid":false,"given":"Steven M.","family":"Goodman","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4573-7551","authenticated-orcid":false,"given":"Erin","family":"Buehler","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Clary","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andy","family":"Coenen","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Donsbach","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8566-6746","authenticated-orcid":false,"given":"Tiffanie N.","family":"Horne","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7896-0605","authenticated-orcid":false,"given":"Michal","family":"Lahav","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"MacDonald","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rain Breaw","family":"Michaels","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajit","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahima","family":"Pushkarna","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joel","family":"Riley","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Santana","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Shi","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rachel","family":"Sweeney","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Phil","family":"Weaver","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ann","family":"Yuan","sequence":"additional","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meredith Ringel","family":"Morris","sequence":"additional","affiliation":[{"name":"Google Research, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown T.","year":"2020","unstructured":"Brown, T. et al. Language models are few-shot learners. Advances in neural information processing systems 33, (2020), 1877\u20131901.","journal-title":"Advances in neural information processing systems"},{"key":"e_1_3_1_3_2","unstructured":"Carlini N. et al. Extracting training data from large language models Dec. 2020."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1002\/dys.1457"},{"key":"e_1_3_1_5_2","first-page":"7282","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Intern. Joint Conf. on Natural Language Processing (Volume 1: Long Papers)","author":"Clark E.","year":"2021","unstructured":"Clark, E. et al. All that\u2019s \u2018human\u2019 is not gold: Evaluating human evaluation of generated text. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Intern. Joint Conf. on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics, Aug. 2021, 7282\u20137296, Online."},{"key":"e_1_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Dhamala J. et al. Bold: Dataset and metrics for measuring biases in open-ended language generation. In Proceedings of the 2021 ACM conf. on fairness accountability and transparency 2021 862\u2013872.","DOI":"10.1145\/3442188.3445924"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300526"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3544819"},{"key":"e_1_3_1_9_2","unstructured":"International Dyslexia Association Editorial Contributors. Dyslexia basics 2020."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3415234"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501931"},{"key":"e_1_3_1_12_2","unstructured":"Li A.Q. Sbattella L. and Tedesco R. PoliSpell: An adaptive spellchecker and predictor for people with dyslexia 2013."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3356727"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173609"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1080\/03075070600572173"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.3402\/rlt.v14i1.10940"},{"issue":"8","key":"e_1_3_1_17_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford A.","year":"2019","unstructured":"Radford, A. et al. Language models are unsupervised multitask learners. OpenAI blog 1, 8, (2019), 9.","journal-title":"OpenAI blog"},{"key":"e_1_3_1_18_2","first-page":"1","volume-title":"Proceedings of the 10th Intern. Cross-Disciplinary Conf. on Web Accessibility, number Article 15 in W4A \u201913","author":"Rello L.","year":"2013","unstructured":"Rello, L., Baeza-Yates, R., Bott, S., and Saggion, H. Simplify or help? text simplification strategies for people with dyslexia. In Proceedings of the 10th Intern. Cross-Disciplinary Conf. on Web Accessibility, number Article 15 in W4A \u201913. Association for Computing Machinery, New York, NY, USA, May 2013, 1\u201310."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2700648.2809850"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858204"},{"key":"e_1_3_1_21_2","unstructured":"Thoppilan R. et al. LaMDA: Language models for dialog applications Jan. 2022."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581560"},{"key":"e_1_3_1_23_2","volume-title":"\u201cAccept the Idea That Neurodiverse Kids Exist\u201d: Dyslexic Narratives and Neurodiversity Paradigm Visions","author":"van Schaik M.","year":"2021","unstructured":"van Schaik, M. \u201cAccept the Idea That Neurodiverse Kids Exist\u201d: Dyslexic Narratives and Neurodiversity Paradigm Visions. Wilfrid Laurier University, 2021, PhD thesis."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300746"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511105"},{"key":"e_1_3_1_26_2","unstructured":"Zhang M. et al. How language model hallucinations can snowball. arXiv preprint arXiv:2305.13534 2023."},{"key":"e_1_3_1_27_2","first-page":"12697","volume-title":"Intern. Conf. on Machine Learning","author":"Zhao Z.","year":"2021","unstructured":"Zhao, Z. et al. Calibrate before use: Improving few-shot performance of language models. In Intern. Conf. on Machine Learning. PMLR, 2021, 12697\u201312706."}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626952","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:15Z","timestamp":1750290255000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626952"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,26]]},"references-count":26,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["10.1145\/3626952"],"URL":"https:\/\/doi.org\/10.1145\/3626952","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,26]]},"assertion":[{"value":"2024-08-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}