{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T04:45:09Z","timestamp":1779165909110,"version":"3.51.4"},"reference-count":81,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T00:00:00Z","timestamp":1738108800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Big Data &amp; Society"],"published-print":{"date-parts":[[2025,3]]},"abstract":"<jats:p>This article proposes a new integration of linguistic anthropology and machine learning (ML) around convergent interests in both the underpinnings of language and making language technologies more socially responsible. While linguistic anthropology focuses on interpreting the cultural basis for human language use, the ML field of interpretability is concerned with uncovering the patterns that Large Language Models (LLMs) learn from human verbal behavior. Through the analysis of a conversation between a human user and an LLM-powered chatbot, we demonstrate the theoretical feasibility of a new, conjoint field of inquiry, cultural interpretability (CI). By focusing attention on the communicative competence involved in the way human users and AI chatbots coproduce meaning in the articulatory interface of human-computer interaction, CI emphasizes how the dynamic relationship between language and culture makes contextually sensitive, open-ended conversation possible. We suggest that, by examining how LLMs internally \u201crepresent\u201d relationships between language and culture, CI can: (1) provide insight into long-standing linguistic anthropological questions about the patterning of those relationships; and (2) aid model developers and interface designers in improving value alignment between language models and stylistically diverse speakers and culturally diverse speech communities. Our discussion proposes three critical research axes: relativity, variation, and indexicality.<\/jats:p>","DOI":"10.1177\/20539517241303118","type":"journal-article","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T14:09:22Z","timestamp":1738159762000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":15,"title":["Toward cultural interpretability: A linguistic anthropological framework for describing and evaluating large language models"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6435-7066","authenticated-orcid":false,"given":"Graham M","family":"Jones","sequence":"first","affiliation":[{"name":"Anthropology, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2750-7306","authenticated-orcid":false,"given":"Shai","family":"Satran","sequence":"additional","affiliation":[{"name":"Sociology and Anthropology, Tel Aviv University, Tel Aviv, IL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5564-635X","authenticated-orcid":false,"given":"Arvind","family":"Satyanarayan","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence (CSAIL), Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,1,29]]},"reference":[{"key":"bibr1-20539517241303118","doi-asserted-by":"crossref","unstructured":"AlKhamissi B, ElNokrashy M, AlKhamissi M, et al. (2024) Investigating cultural alignment of large language models. Available at: https:\/\/doi.org\/10.48550\/arXiv.2402.13231 (accessed 14 March 2024).","DOI":"10.18653\/v1\/2024.acl-long.671"},{"issue":"1","key":"bibr2-20539517241303118","first-page":"58","volume":"37","author":"Bajohr H","year":"2023","journal-title":"IMAGE"},{"key":"bibr3-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1145\/332040.332473"},{"key":"bibr4-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1515\/9780691245058"},{"key":"bibr5-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"bibr6-20539517241303118","volume-title":"Race After Technology: Abolitionist Tools for the New Jim Code","author":"Benjamin R","year":"2019"},{"key":"bibr7-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-021-01582-9"},{"key":"bibr8-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511813085"},{"key":"bibr9-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1177\/20539517231188725"},{"key":"bibr10-20539517241303118","first-page":"143","volume-title":"Language and Desire","author":"Channell J","year":"1997"},{"key":"bibr11-20539517241303118","unstructured":"Chomsky N, Roberts I, Watumull J (2023) The false promise of ChatGPT.\n                      New York Times\n                      , 8 March. Available at: https:\/\/www.nytimes.com\/2023\/03\/08\/opinion\/noam-chomsky-chatgpt-ai.html (accessed 3 August 2023)."},{"key":"bibr12-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-023-01710-4"},{"key":"bibr13-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1515\/cog-2014-0024"},{"key":"bibr14-20539517241303118","first-page":"77","volume-title":"Rethinking Context: Language as an Interactive Phenomenon","author":"Duranti A","year":"1992"},{"key":"bibr15-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1086\/368118"},{"key":"bibr16-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1017\/9781316403242"},{"key":"bibr17-20539517241303118","volume-title":"Automating Inequality: How High-tech Tools Profile, Police, and Punish the Poor","author":"Eubanks V","year":"2018"},{"key":"bibr18-20539517241303118","doi-asserted-by":"crossref","unstructured":"Farid Adilazuarda M, Mukherjee S, Lavania P, et al. (2024) Towards measuring and modeling \u201cculture\u201d in LLMs: A survey. Available at: https:\/\/doi.org\/10.48550\/arXiv.2403.15412 (accessed 14 March 2024).","DOI":"10.18653\/v1\/2024.emnlp-main.882"},{"key":"bibr19-20539517241303118","doi-asserted-by":"publisher","DOI":"10.2307\/768167"},{"key":"bibr20-20539517241303118","unstructured":"Galt J (2023) Bing and other AI programs are meant to behave like humans. Why are we shocked when they do?\n                      LA Times\n                      , 24 February. Available at: https:\/\/www.latimes.com\/entertainment-arts\/story\/2023-02-24\/commentary-ai-bing-chatgpt-sentient-human-creators (accessed 25 July 2023)."},{"key":"bibr21-20539517241303118","unstructured":"Gehrmann S, Adewumi T, Aggarwal K, et al. (2021) The GEM benchmark: Natural language generation, its evaluation and metrics. Available at: https:\/\/doi.org\/10.48550\/arXiv.2102.01672 (accessed 3 November 2023)."},{"key":"bibr22-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13715"},{"key":"bibr23-20539517241303118","doi-asserted-by":"publisher","DOI":"10.30676\/jfas.137824"},{"key":"bibr24-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1016\/0378-2166(83)90089-9"},{"key":"bibr25-20539517241303118","unstructured":"Harari Y, Harris T, Raskin A (2023) You can have the blue pill or the red pill, and we\u2019re out of blue pills.\n                      New York Times\n                      , 24 March. Available at: https:\/\/www.nytimes.com\/2023\/03\/24\/opinion\/yuval-harari-ai-chatgpt.html (accessed 23 July 2023)."},{"key":"bibr26-20539517241303118","unstructured":"Heaven WD (2023) The inside story of how ChatGPT was built from the people who made it.\n                      MIT Technology Review,\n                      3 March. Available at: https:\/\/www.technologyreview.com\/2023\/03\/03\/1069311\/inside-story-oral-history-how-chatgpt-built-openai\/ (accessed 9 April 2023)."},{"key":"bibr27-20539517241303118","unstructured":"Herrman J (2023) Why Bing is being creepy.\n                      New York\n                      , 16 February. Available at: https:\/\/nymag.com\/intelligencer\/2023\/02\/why-bing-is-being-creepy.html (accessed 22 July 2023)."},{"key":"bibr28-20539517241303118","first-page":"269","volume-title":"Sociolinguistics: Selected Readings","author":"Hymes D","year":"1972"},{"key":"bibr29-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1075\/z.61.08hym"},{"key":"bibr30-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1111\/j.1556-3502.2010.51306.x"},{"key":"bibr31-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1016\/j.langcom.2007.09.003"},{"key":"bibr32-20539517241303118","unstructured":"Keane W, Shapiro SJ (2023) Deus ex machina: The dangers of AI godbots.\n                      The Spectator\n                      , 29 July. Available at: https:\/\/www.spectator.co.uk\/article\/deus-ex-machina-the-dangers-of-ai-godbots\/ (accessed 8 November 2023)."},{"key":"bibr33-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1002\/9780470996522.ch8"},{"key":"bibr34-20539517241303118","unstructured":"Klein E (2023) The imminent danger of A.I. is one we\u2019re not talking about.\n                      New York Times\n                      , 26 February. Available at: https:\/\/www.nytimes.com\/2023\/02\/26\/opinion\/microsoft-bing-sydney-artificial-intelligence.html (accessed 25 July 2023)."},{"key":"bibr35-20539517241303118","unstructured":"Li C, Chen M, Wang J, et al. (2024) CultureLLM: Incorporating cultural differences into large language models. Available at: https:\/\/doi.org\/10.48550\/arXiv.2402.10946 (accessed 14 March 2024)."},{"key":"bibr36-20539517241303118","doi-asserted-by":"crossref","unstructured":"Linzen T (2020) How can we accelerate progress towards human-like linguistic generalization? Available at: https:\/\/doi.org\/10.48550\/arXiv.2005.00955 (accessed 3 November 2023).","DOI":"10.18653\/v1\/2020.acl-main.465"},{"key":"bibr37-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"bibr38-20539517241303118","unstructured":"Magueresse A, Carles V, Heetderks E (2020) Low-resource languages: A review of past work and future challenges. Available at: https:\/\/doi.org\/10.48550\/arXiv.2006.07264 (accessed 14 March 2024)."},{"key":"bibr39-20539517241303118","doi-asserted-by":"crossref","unstructured":"Maleki N, Padmanabhan B, Dutta K (2024) AI hallucinations: A misnomer worth clarifying. Available at: https:\/\/doi.org\/10.48550\/arXiv.2401.06796 (accessed 14 March 2024).","DOI":"10.1109\/CAI59869.2024.00033"},{"key":"bibr40-20539517241303118","unstructured":"Marcus G (2022) How come GPT can seem so brilliant one minute and so breathtakingly dumb the next? The Road to AI We Can Trust. Available at: https:\/\/garymarcus.substack.com\/p\/how-come-gpt-can-seem-so-brilliant (accessed 13 August 2023)."},{"key":"bibr41-20539517241303118","unstructured":"Masoud RI, Liu Z, Ferianc M, et al. (2023) Cultural alignment in large language models: An explanatory analysis based on Hofstede\u2019s cultural dimensions. Available at: https:\/\/doi.org\/10.48550\/arXiv.2309.12342 (accessed 14 March 2024)."},{"key":"bibr42-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1017\/S0047404500010915"},{"key":"bibr43-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1002\/9781118786093.iela0474"},{"key":"bibr44-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9481.00163"},{"key":"bibr45-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1177\/20539517211069891"},{"key":"bibr46-20539517241303118","doi-asserted-by":"publisher","DOI":"10.18574\/nyu\/9781479833641.001.0001"},{"key":"bibr47-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1177\/1463499612454088"},{"key":"bibr48-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1177\/1754073921990733"},{"key":"bibr49-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1002\/9781118325001.ch35"},{"key":"bibr50-20539517241303118","first-page":"284","volume-title":"Metaphor And Thought","author":"Reddy M","year":"1979"},{"key":"bibr51-20539517241303118","unstructured":"Riskin J (2023) A sort of buzzing inside my head.\n                      New York Review of Books\n                      , 25 June. Available at: https:\/\/www.nybooks.com\/online\/2023\/06\/25\/a-sort-of-buzzing-inside-my-head\/ (accessed 4 August 2023)."},{"key":"bibr52-20539517241303118","unstructured":"Roose K (2023a) Bing\u2019s A.I. chat: \u201cI want to be alive \u201d.\n                      New York Times\n                      , 16 February. Available at: https:\/\/www.nytimes.com\/2023\/02\/16\/technology\/bing-chatbot-transcript.html (accessed 18 February 2023)."},{"key":"bibr53-20539517241303118","unstructured":"Roose K (2023b) A conversation with Bing\u2019s chatbot left me deeply unsettled.\n                      New York Times\n                      , 16 February. Available at: https:\/\/www.nytimes.com\/2023\/02\/16\/technology\/bing-chatbot-microsoft-chatgpt.html (accessed 18 February 2023)."},{"key":"bibr54-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1002\/9781444328301"},{"key":"bibr55-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-023-00373-7"},{"key":"bibr56-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-anthro-102218-011243"},{"key":"bibr57-20539517241303118","doi-asserted-by":"publisher","DOI":"10.21428\/e4baedd9.2d7598a2"},{"key":"bibr58-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1353\/lan.1977.0041"},{"key":"bibr59-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1177\/2053951717738104"},{"key":"bibr60-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501972"},{"key":"bibr61-20539517241303118","doi-asserted-by":"publisher","DOI":"10.7560\/777682-005"},{"key":"bibr62-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1086\/665697"},{"key":"bibr63-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1086\/423971"},{"key":"bibr64-20539517241303118","unstructured":"Singh C, Inala JP, Galley M, et al. (2024) Rethinking interpretability in the era of large language models. Available at: https:\/\/doi.org\/10.48550\/arXiv.2402.01761 (accessed 14 March 2024)."},{"key":"bibr65-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1002\/9781119780830.ch31"},{"key":"bibr66-20539517241303118","volume-title":"Human-Machine Reconfigurations: Plans and Situated Actions, 2nd edition","author":"Suchman LA","year":"2007"},{"key":"bibr67-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1177\/20539517231206794"},{"key":"bibr68-20539517241303118","doi-asserted-by":"crossref","unstructured":"Tang BJ, Boggust A, Satyanarayan A (2023) Vistext: A benchmark for semantically rich chart captioning. Available at: https:\/\/doi.org\/10.48550\/arXiv.2307.05356 (accessed 3 November 2023).","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"bibr69-20539517241303118","doi-asserted-by":"publisher","DOI":"10.2307\/415006"},{"key":"bibr70-20539517241303118","author":"Thelot R","year":"2023","journal-title":"AI & Society"},{"key":"bibr71-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1093\/mind\/LIX.236.433"},{"key":"bibr72-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1145\/365153.365168"},{"key":"bibr73-20539517241303118","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4543807"},{"key":"bibr74-20539517241303118","doi-asserted-by":"publisher","DOI":"10.7208\/chicago\/9780226828329.001.0001"},{"key":"bibr75-20539517241303118","unstructured":"Wolf Y, Wies N, Levine Y, et al. (2023) Fundamental limitations of alignment in large language models. Available at: https:\/\/doi.org\/10.48550\/arXiv.2304.11082 (accessed 14 March 2024)."},{"key":"bibr76-20539517241303118","first-page":"73","volume-title":"A Companion to Linguistic Anthropology","author":"Woolard KA","year":"2004"},{"key":"bibr77-20539517241303118","unstructured":"Wynn A, Sucholutsky I, Griffiths TL (2023) Learning human-like representations to enable learning human values. Available at: https:\/\/doi.org\/10.48550\/arXiv.2312.14106 (accessed 14 March 2024)."},{"key":"bibr78-20539517241303118","doi-asserted-by":"crossref","unstructured":"Xu S, Dong W, Guo Z, et al. (2024) Exploring multilingual human value concepts in large language models: Is value alignment consistent, transferable and controllable across languages? Available at: https:\/\/doi.org\/10.48550\/arXiv.2402.18120 (accessed 14 March 2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.96"},{"key":"bibr79-20539517241303118","unstructured":"Yang D, Hovy D, Jurgens D, et al. (2024) The call for socially aware language technologies. Available at: https:\/\/doi.org\/10.48550\/arXiv.2405.02411 (accessed 18 September 2024)."},{"key":"bibr80-20539517241303118","doi-asserted-by":"publisher","DOI":"10.1145\/3639372"},{"key":"bibr81-20539517241303118","unstructured":"Zou A, Phan L, Chen S, et al. (2023) Representation engineering: A top-down approach to AI transparency. Available at: https:\/\/doi.org\/10.48550\/arXiv.2310.01405 (accessed 14 March 2024)."}],"container-title":["Big Data &amp; Society"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20539517241303118","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20539517241303118","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20539517241303118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:01:04Z","timestamp":1777381264000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20539517241303118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,29]]},"references-count":81,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10.1177\/20539517241303118"],"URL":"https:\/\/doi.org\/10.1177\/20539517241303118","relation":{},"ISSN":["2053-9517","2053-9517"],"issn-type":[{"value":"2053-9517","type":"print"},{"value":"2053-9517","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,29]]},"article-number":"20539517241303118"}}