Gendered Mental Health Stigma in Masked Language Models
Open accessAbstract
Mental health stigma prevents many individuals from receiving the appropriate care, and social psychology studies have shown that mental health tends to be overlooked in men.In this work, we investigate gendered mental health stigma in masked language models.In doing so, we operationalize mental health stigma by developing a framework grounded in psychology research: we use clinical psychology literature to curate prompts, then evaluate the models' propensity to generate gendered words.We find that masked language models capture societal stigma about gender in mental health: models are consistently more likely to predict female subjects than male in sentences about having a mental health condition (32% vs. 19%), and this disparity is exacerbated for sentences that indicate treatment-seeking behavior.Furthermore, we find that different models capture dimensions of stigma differently for men and women, associating stereotypes like anger, blame, and pity more with women with mental health conditions than with men.In showing the complex nuances of models' gendered mental health stigma, we demonstrate that context and overlapping dimensions of identity are important considerations when assessing computational models' social biases.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Instruction prompt fine-tuning can increase inaccurate or inappropriate content.
“Conversely, however, instruction prompt fine-tuning can also increase inaccurate or inappropriate content [55]”
From The Opportunities and Risks of Large Language Models in Mental Health (2024) · cites this paper as [55]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Mapping the Margins: Intersectionality, Identity Politics, and Violence against Women of Color
Crenshaw, K. (1991) · Stanford Law Review · doi:10.2307/1229039 · Cited by 29,585 · see citing works
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · see citing works
An Attribution Model of Public Discrimination Towards Persons with Mental Illness
Corrigan, P., Markowitz, F. E., Watson, A., Rowan, D., & Kubiak, M. A. (2003) · Journal of Health and Social Behavior · doi:10.2307/1519806 · Cited by 1,407 · see citing works
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050 · see citing works
Schäfer, T., & Schwarz, M. A. (2019) · Frontiers in Psychology · doi:10.3389/fpsyg.2019.00813 · Cited by 774 · see citing works
Schwarzer, R., Lippke, S., & Luszczynska, A. (2011) · Rehabilitation Psychology · doi:10.1037/a0024509 · Cited by 743 · see citing works
Gender bias in coreference resolution: Evaluation and debiasing methods
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2003 · Cited by 684 · see citing works
StereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.416 · Cited by 643 · see citing works
Methods in predictive techniques for mental health status on social media: a critical review
Chancellor, S., & De Choudhury, M. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0233-7 · Cited by 557 · see citing works
Raghupathi, W., & Raghupathi, V. (2018) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph15030431 · Cited by 540 · see citing works
Sharma, A., Lin, I. W., Miner, A. S., Atkins, D. C., & Althoff, T. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-022-00593-2 · Cited by 500 · see citing works
Self-citationCrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
Nangia, N., Vania, C., Bhalerao, R., & Bowman, S. R. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.154 · Cited by 446 · see citing works
Gender Bias in Coreference Resolution
Rudinger, R., Naradowsky, J., Leonard, B., & Van Durme, B. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2002 · Cited by 443 · see citing works
Racial Bias in Hate Speech and Abusive Language Detection Datasets
Davidson, T., Bhattacharya, D., & Weber, I. (2019) · Proceedings of the Third Workshop on Abusive Language Online · doi:10.18653/v1/w19-3504 · Cited by 414 · see citing works
Non-binary/Genderqueer Identities: a Critical Review of the Literature
Matsuno, E. G., & Budge, S. L. (2017) · Current Sexual Health Reports · doi:10.1007/s11930-017-0111-8 · Cited by 341 · see citing works
MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare
Ji, S., Zhang, T., Ansari, L., Fu, J., Tiwari, P., & Cambria, E. (2022) · Proceedings of the Language Resources and Evaluation Conference · doi:10.63317/2d7umxifj8wz · Cited by 233 · see citing works
Mental health stigma update: a review of consequences
Sickel, A. E., Seacat, J. D., & Nabors, N. A. (2014) · Advances in Mental Health · doi:10.1080/18374905.2014.11081898 · Cited by 224 · see citing works
Males and Mental Health Stigma
Chatmon, B. N. (2020) · American Journal of Men s Health · doi:10.1177/1557988320949322 · Cited by 221 · see citing works
Sharma, A. K., Lin, I. W., Miner, A. S., Atkins, D. C., & Althoff, T. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3450097 · Cited by 168 · see citing works
Self-citationArtificial Intelligence in mental health and the biases of language based models
Straw, I., & Callison-Burch, C. (2020) · PLOS ONE · doi:10.1371/journal.pone.0240376 · Cited by 164 · see citing works
Towards Understanding and Mitigating Social Biases in Language Models
Liang, P. P., Wu, C., Morency, L.-P., & Salakhutdinov, R. (2021) · arXiv · doi:10.48550/arxiv.2106.13219 · Cited by 153 · see citing works
Assessing Social and Intersectional Biases in Contextualized Word RepresentationsPreprint
Tan, Y. C., & Celis, L. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01485 · Cited by 142 · see citing works
Garrido-Muñoz, I., Montejo-Ráez, A., Martínez-Santiago, F., & Ureña-López, L. A. (2021) · Applied Sciences · doi:10.3390/app11073184 · Cited by 123 · see citing works
A Survey of Race, Racism, and Anti-Racism in NLP
Field, A., Blodgett, S. L., Talat, Z., & Tsvetkov, Y. (2021) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2021.acl-long.149 · Cited by 94 · see citing works
Self-citationClinical-Longformer and Clinical-BigBird: Transformers for long clinical sequencesPreprint
Li, Y., Wehbe, R. M., Ahmad, F. S., Wang, H., & Luo, Y. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.11838 · Cited by 65 · see citing works
Unsupervised Discovery of Implicit Gender Bias
Field, A., & Tsvetkov, Y. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.44 · Cited by 50 · see citing works
Self-citationBalancing Objectives in Counseling Conversations: Advancing Forwards or Looking Backwards
Zhang, J., & Danescu-Niculescu-Mizil, C. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.470 · Cited by 48 · see citing works
Fast, E., Vachovsky, T., & Bernstein, M. S. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v10i1.14744 · Cited by 43 · see citing works
Controlled Analyses of Social Biases in Wikipedia Bios
Field, A., Park, C. Y., Lin, K., & Tsvetkov, Y. (2020) · The Web Conference · doi:10.1145/3485447.3512134 · Cited by 31 · see citing works
Self-citationSharma, A. K., Lin, I. W., Miner, A. S., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.15144 · Cited by 23 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 2
- Patricia Hill Collins and Sirma Bilge. 2020. Intersec- tionality. John Wiley & Sons.
- Patrick Corrigan and Amy Watson. 2002. The impact of stigma on people with mental illness. World psy- chiatry : official journal of the World Psychiatric Association (WPA), 1:16-20.
Cited by
Sorted by citations
The Opportunities and Risks of Large Language Models in Mental Health
Lawrence, H. R., Schneider, R. A., Rubin, S. B., Matarić, M. J., McDuff, D. J., & Jones Bell, M. (2024) · JMIR Mental Health · doi:10.2196/59479 · Cited by 235 · see citing works
Feng, S., Park, C. Y., Liu, Y., & Tsvetkov, Y. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.656 · Cited by 149 · see citing works
Self-citationSharma, A., Rushton, K., Lin, I. W., Nguyen, T., & Althoff, T. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642761 · Cited by 119 · see citing works
Self-citationCognitive Reframing of Negative Thoughts through Human-Language Model Interaction
Sharma, A., Rushton, K., Lin, I. W., Wadden, D., Lucas, K., Miner, A. S., Nguyen, T., & Althoff, T. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.555 · Cited by 76 · see citing works
Self-citationLanguage Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey
Kumar, S., Balachandran, V., Njoo, L., Anastasopoulos, A., & Tsvetkov, Y. (2023) · Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.241 · Cited by 38 · see citing works
Self-citationExamining risks of racial biases in NLP tools for child protective services
Field, A., Coston, A., Gandhi, N., Chouldechova, A., Putnam-Hornstein, E., Steier, D., & Tsvetkov, Y. (2023) · 2023 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3593013.3594094 · Cited by 18 · see citing works
Self-citationOn the State of NLP Approaches to Modeling Depression in Social Media: A Post-COVID-19 Outlook
Bucur, A.-M., Moldovan, A.-C., Parvatikar, K., Zampieri, M., KhudaBukhsh, A. R., & Dinu, L. P. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3540507 · Cited by 15 · see citing works
Hornstein, S., Scharfenberger, J., Lueken, U., Wundrack, R., & Hilbert, K. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01121-9 · Cited by 10 · see citing works
Identifying Gender Bias in Generative Models for Mental Health Synthetic Data
Lozoya, D. C., D’Alfonso, S., & Conway, M. (2023) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi57859.2023.00109 · Cited by 8 · see citing works
The Expression of Happiness in Social Media of Individuals Reporting Depression
Bucur, A.-M., Chulvi, B., Cosma, A., & Rosso, P. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3434482 · Cited by 4 · see citing works
Go beyond the individual: an intersectional perspective on mental illness stigma in ChinaPreprint
Lin, Z. (2023) · Research Square · doi:10.21203/rs.3.rs-2851490/v1 · Cited by 3 · see citing works
Evaluating AI-based Mental Health Interventions
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749733 · Cited by 1 · see citing works
Self-citationLogic-driven Indirect Supervision: An Application to Crisis Counseling
Grespan, M. M., Broadbent, M., Zhang, X., Axford, K., Kious, B. M., Imel, Z. E., & Srikumar, V. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.654 · Cited by 1 · see citing works
The Expression of Happiness in Social Media of Individuals Diagnosed With DepressionPreprint
Bucur, A.-M., Chulvi, B., Cosma, A., & Rosso, P. (2023) · doi:10.36227/techrxiv.23264507.v1 · Cited by 1 · see citing works
The Expression of Happiness in Social Media of Individuals Diagnosed With DepressionPreprint
Bucur, A.-M., Chulvi, B., Cosma, A., & Rosso, P. (2023) · doi:10.36227/techrxiv.23264507
Judijanto, L. (2025) · Journal of Information System Technology and Engineering · doi:10.61487/jiste.v3i2.145
Le parole della discriminazione
Biemmi, I., Viviani, A., & Biemmi, I. (2025) · doi:10.36253/979-12-215-0715-7
Mallon, C., Murphy, T., McFarlane, S., Gorman, C., Mulvenna, M. D., Gorman, J., McTear, M., Bond, R. R., & Ennis, E. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227816
MacDermid, J. C., Fletcher, A., Killip, S. C., Brazil, A., Ricciardelli, R., & Bromhead, R. C. (2026) · Occupation and Health · doi:10.3390/occuphealth1010010
Psyche and pixels: AI-generated images and their impact on stigma of mental illnesses in Germany
Grimmer, J., Khorikian–Ghazari, N., Hasan, A., Hartmann, N. L., Schoch, L., Greiner, S.-K., Leucht, S., & Papazova, I. (2026) · Journal of Psychiatric Research · doi:10.1016/j.jpsychires.2026.04.029
PERSONALITY TRAITS AND SOCIAL MEDIA'S IMPACT ON MENTAL ILLNESS STIGMA IN HIGHER EDUCATION
Selamat, T., Bakar, A. A., Zalli, M. M. M., Othman, M. S., & Dagang, M. M. (2026) · International Journal of Entrepreneurship and Management Practices · doi:10.35631/ijepc.1163062
Supplementary Material for Evaluating AI-Based Mental Health Interventions
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749737
Self-citationHuman–AI Collaboration to Empower People Seeking Support
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749732
Self-citation(2026) · ACM eBooks · doi:10.1145/3749728.3749738
(2026) · ACM eBooks · doi:10.1145/3749728.3749739
Supplementary Materials for Human–AI Collaboration to Empower People Providing Support
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749735
Self-citationHuman–AI Collaboration to Empower People Providing Support
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749731
Self-citationSharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749730
Self-citation(2026) · ACM eBooks · doi:10.1145/3749728.3749729
Supplementary Materials for Human–AI Collaboration to Empower People Seeking Support
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749736
Self-citation(2026) · ACM eBooks · doi:10.1145/3749728.3749734
Kim, S., Kim, H. M., Kim, K., & Zhu, D. (2026) · Social Science & Medicine · doi:10.1016/j.socscimed.2026.119855
- Authors
- Lin, I., Njoo, L., Field, A., Sharma, A., Reinecke, K., Althoff, T., & Tsvetkov, Y.
- Affiliations
- University of Washington (US)
- Stanford University (US)
- Venue
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Published
- 2022
- Pages
- 2152-2170
- OpenAlex
- W4385572715
- Cited by
- 33
- References
- 30
- Citations by year
- 2026: 15 · 2025: 5 · 2024: 4 · 2023: 9
- FWCI
- 4.47
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- National Science Foundation (2142794, 2040926, 2006104, 2142739, 2025022, CAREER, 1901386)
- Bill and Melinda Gates Foundation (INV-004841)
- Alfred P. Sloan Foundation
- University of Washington
- National Institutes of Health
- Office of Naval Research (#N00014-21-1-2154, N00014)
- National Institute of Mental Health (R01MH125179)
- Topics
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Social Sciences › Psychology › Social Psychology › Mental Health Treatment and Access
- Social Sciences › Psychology › Social Psychology › LGBTQ Health, Identity, and Policy
- Keywords
- mental health stigma, gender bias, masked language models, gender stereotypes, treatment-seeking behavior, gendered language, clinical psychology
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
