The DOI matches its Crossref record; 41 of the 43 references it cites were found in a registry or an index.
Social Biases in NLP Models as Barriers for Persons with Disabilities
Open accessAbstract
Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models.In particular, representations encoded in models often inadvertently perpetuate undesirable social biases from the data on which they are trained.In this paper, we present evidence of such undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis.Next, we demonstrate that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases towards mentions of disability.We end by highlighting topical biases in the discourse about disability which may contribute to the observed model biases; for instance, gun violence, homelessness, and drug addiction are over-represented in texts discussing mental illness.
Overview
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
Verification
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“From negative sentiment and toxicity directed towards some social groups, to stereotypical linguistic associations, to lack of recognition of certain language dialects, the presence of biases of LLMs have been well-documented ( e.g. , Blodgett and O'Connor 2017; Hutchinson et al. 2020; Mei, Fereidooni, and Caliskan 2023; Mˇ echura 2022; Mozafari, Farahbakhsh, and Crespi 2020; Sap et al. 2019; Shen”
From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Hutchinson et al. 2020
Experimental — accuracy not yet measuredIn the citing paper
“Text suggestions based on language models have been known to inherit biases and dominant 'views' from the text corpus used to train the language model [22,39,43,55].”
From Interacting with Next-Phrase Suggestions: How Suggestion Systems Aid and Influence the Cognitive Processes of Writing (2023) · cites this paper as [39]
In the citing paper
“LLMs learn from web-sourced text data, acquiring inherent biases (31–33) and—in some cases—replicate excerpts from their training data (34).”
From How should the advancement of large language models affect the practice of science? (2025) · cites this paper as [33]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
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 54,325
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
Algorithms of oppression: how search engines reinforce racism
Polynczuk-Alenius, K. (2019) · Information, Communication & Society · doi:10.1080/1369118x.2019.1593485 · Cited by 2,934
Semantics derived automatically from language corpora contain human-like biases
Caliskan, A., Bryson, J. J., & Narayanan, A. (2017) · Science · doi:10.1126/science.aal4230 · Cited by 2,887
Algorithms of Oppression: How Search Engines Reinforce Racism
Noble, S. U. (2020) · doi:10.2307/j.ctt1pwt9w5 · Cited by 2,709
Model Cards for Model Reporting
Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287596 · Cited by 2,681
Self-citationA Synopsis of Linguistic Theory, 1930-1955
Firth, J. R. (1957) · Medical Entomology and Zoology · Cited by 1,675
Fairness and Abstraction in Sociotechnical Systems
Selbst, A. D., Boyd, D., Friedler, S. A., Venkatasubramanian, S., & Vertesi, J. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287598 · Cited by 1,631
Research works printed but not linked: 4
- Su Lin Blodgett, Solon Barocas, Hal III Daume, and Hanna Wallach. 2020. Language (technology) is power: The need to be explicit about NLP harms. In Proceedings of the Annual Meeting of the Associ- ation for Computational Lingustics (ACL).
- Alexander D'Amour, Hansa Srinivasan, James At- wood, Pallavi Baljekar, D Sculley, and Yoni Halpern. 2020. Fairness is not static: Deeper understanding of long term fairness via simulation studies. In Pro- ceedings of the 2020 Conference on Fairness, Ac- countability, and Transparency, pages 525-534.
- Donald Martin Jr., Vinodkumar Prabhakaran, Jill Kuhlberg, Andrew Smart, and William Isaac. 2020. Participatory problem formulation for fairer ma- chine learning through community based system dy- namics approach. In ICLR Workshop on Machine Learning in Real Life (ML-IRL).
- Deirdre K Mulligan, Joshua A Kroll, Nitin Kohli, and Richmond Y Wong. 2019. This thing called fairness: Disciplinary confusion realizing a value in technol- ogy. Proceedings of the ACM on Human-Computer Interaction, 3(CSCW):1-36.
Cited by
Sorted by citations
Items 301–301 of 301
11 AI and Ecology: Climate Metaphors in Texts Generated by LLMs
Kwaśniewska, M. (2026) · V&R unipress eBooks · doi:10.14220/9783737020503.201
Metadata
- Authors
- Hutchinson, B., Prabhakaran, V., Denton, E., Webster, K., Zhong, Y., & Denuyl, S.
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 5491-5501
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W3035296331
- Cited by
- 274
- References
- 43
- Citations by year
- 2026: 21 · 2025: 41 · 2024: 44 · 2023: 66 · 2022: 44 · 2021: 48 · 2020: 10
- FWCI
- 43.56
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Social Sciences › Sociology and Political Science › Disability Rights and Representation
- Keywords
- social bias, disability, natural language processing models, toxicity prediction, sentiment analysis, neural embeddings, bias in language models, mental illness discourse, inclusive technology, disability representation
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
