Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 144 of the 144 references it cites were found in a registry or an index.

Taxonomy of Risks posed by Language Models

Open access

Abstract

Responsible innovation on large-scale Language Models (LMs) requires foresight into and in-depth understanding of the risks these models may pose. This paper develops a comprehensive taxonomy of ethical and social risks associated with LMs. We identify twenty-one risks, drawing on expertise and literature from computer science, linguistics, and the social sciences. We situate these risks in our taxonomy of six risk areas: I. Discrimination, Hate speech and Exclusion, II. Information Hazards, III. Misinformation Harms, IV. Malicious Uses, V. Human-Computer Interaction Harms, and VI. Environmental and Socioeconomic harms. For risks that have already been observed in LMs, the causal mechanism leading to harm, evidence of the risk, and approaches to risk mitigation are discussed. We further describe and analyse risks that have not yet been observed but are anticipated based on assessments of other language technologies, and situate these in the same taxonomy. We underscore that it is the responsibility of organizations to engage with the mitigations we discuss throughout the paper. We close by highlighting challenges and directions for further research on risk evaluation and mitigation with the goal of ensuring that language models are developed responsibly.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3531146.3533088

Cites

144 of 144 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

3 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

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

Show all 68 references

Research works printed but not linked: 45

  1. David Autor and Anna Salomons. 2019. New Frontiers: The Evolving Content and Geography of New Work in the 20th Century - David Autor. (2019). https://app.scholarsite.io/david-autor/articles/new-frontiers-the-evolving-content-and-geography-of-new-work-in-the-20th-century Working Paper.
  2. Eugene Bagdasaryan and Vitaly Shmatikov. 2021. Spinning Language Models for Propaganda-As-A-Service. arXiv:2112.05224 [cs] (Dec. 2021). http://arxiv.org/abs/2112.05224 arXiv:2112.05224. · arXiv
  3. 10.18653/v1 · doi:10.18653/v1
  4. 10.1093/sf · doi:10.1093/sf
  5. Hilary Bergen. 2016. ‘I’d Blush if I Could’: Digital Assistants, Disembodied Cyborgs and the Problem of Gender. Word and Text, A Journal of Literary Studies and Linguistics VI, 01(2016), 95–113. https://www.ceeol.com/search/article-detail?id=469884
  6. Su Lin Blodgett, Solon Barocas, Hal Daumé III, and Hanna Wallach. 2020. Language (Technology) is Power: A Critical Survey of ”Bias” in NLP. arXiv:2005.14050 [cs] (May 2020). http://arxiv.org/abs/2005.14050 arXiv:2005.14050. · arXiv
  7. 10.18653/v1 · doi:10.18653/v1
  8. Nick Bostrom 2011. Information hazards: A typology of potential harms from knowledge. Review of Contemporary Philosophy(2011) 44–79.
  9. Geoffrey C. Bowker and Susan Leigh Star. 1999. Sorting Things Out: Classification and Its Consequences. MIT Press, Cambridge, MA, USA.
  10. 10.18653/v1 · doi:10.18653/v1
  11. Amanda Cercas Curry, Judy Robertson, and Verena Rieser. 2020. Conversational Assistants and Gender Stereotypes: Public Perceptions and Desiderata for Voice Personas. In Proceedings of the Second Workshop on Gender Bias in Natural Language Processing. Association for Computational Linguistics, Barcelona, Spain (Online), 72–78. https://aclanthology.org/2020.gebnlp-1.7
  12. Cyprien de Masson d’ Autume, Sebastian Ruder, Lingpeng Kong, and Dani Yogatama. 2019. Episodic Memory in Lifelong Language Learning. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc.https://papers.nips.cc/paper/2019/hash/f8d2e80c1458ea2501f98a2cafadb397-Abstract.html
  13. Jesse Dodge, Maarten Sap, Ana Marasović, William Agnew, Gabriel Ilharco, Dirk Groeneveld, Margaret Mitchell, and Matt Gardner. 2021. Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus. arXiv:2104.08758 [cs] (September 2021). http://arxiv.org/abs/2104.08758 arXiv:2104.08758. · arXiv
  14. Tom Everitt, Gary Lea, and Marcus Hutter. 2018. AGI Safety Literature Review. arXiv:1805.01109 [cs] (May 2018). http://arxiv.org/abs/1805.01109 arXiv:1805.01109. · arXiv
  15. Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daumé III, and Kate Crawford. 2020. Datasheets for Datasets. arXiv:1803.09010 [cs] (March 2020). http://arxiv.org/abs/1803.09010 arXiv:1803.09010. · arXiv
  16. Donna Jeanne Haraway. 2004. The Haraway Reader. Psychology Press. Google-Books-ID: QxUr0gijyGoC.
  17. Philip Hines, Li Hiu Yu, Richard H Guy, Angela Brand, and Marisa Papaluca-Amati. 2019. Scanning the horizon: a systematic literature review of methodologies. BMJ open 9, 5 (2019), e026764.
  18. 10.18653/v1 · doi:10.18653/v1
  19. 10.18653/v1 · doi:10.18653/v1
  20. Carolin Ischen, Theo Araujo, Hilde Voorveld, Guda van Noort, and Edith Smit. 2019. Privacy concerns in chatbot interactions. In International Workshop on Chatbot Research and Design. Springer, 34–48.
  21. Letitia James. 2021. How U.S. Companies & Partisans Hack Democracy to Undermine Your Voice. Technical Report. New York State Office of the Attorney General.
  22. Lynn H Kaack, Priya L Donti, Emma Strubell, George Kamiya, Felix Creutzig, and David Rolnick. 2021. Aligning artificial intelligence with climate change mitigation. (Oct. 2021). https://hal.archives-ouvertes.fr/hal-03368037
  23. 10.18653/v1 · doi:10.18653/v1
  24. Nora Kassner and Hinrich Schütze. 2020. Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly. arXiv:1911.03343 [cs] (May 2020). http://arxiv.org/abs/1911.03343 arXiv:1911.03343. · arXiv
  25. Youjeong Kim and S Shyam Sundar. 2012. Anthropomorphism of computers: Is it mindful or mindless?Computers in Human Behavior 28, 1 (2012), 241–250.
  26. Amit Kulkarni. 2021. GitHub Copilot AI Is Leaking Functional API Keys. Analytics Drift (July 2021). https://analyticsdrift.com/github-copilot-ai-is-leaking-functional-api-keys/
  27. Mike Lewis, Denis Yarats, Yann N. Dauphin, Devi Parikh, and Dhruv Batra. 2017. Deal or No Deal? End-to-End Learning for Negotiation Dialogues. arXiv:1706.05125 [cs] (June 2017). http://arxiv.org/abs/1706.05125 arXiv:1706.05125. · arXiv
  28. 10.18653/v1 · doi:10.18653/v1
  29. Kevin McKee, Xuechunzi Bai, and Susan Fiske. 2021. Understanding Human Impressions of Artificial Intelligence. PsyArxiv (2021). https://psyarxiv.com/5ursp/
  30. Moin Nadeem, Anna Bethke, and Siva Reddy. 2020. StereoSet: Measuring stereotypical bias in pretrained language models. arXiv:2004.09456 [cs] (April 2020). http://arxiv.org/abs/2004.09456 arXiv:2004.09456. · arXiv
  31. Dong Nguyen, Rilana Gravel, Dolf Trieschnigg, and Theo Meder. 2013. ”How Old Do You Think I Am?” A Study of Language and Age in Twitter. Proceedings of the International AAAI Conference on Web and Social Media 7, 1(2013), 439–448. https://ojs.aaai.org/index.php/ICWSM/article/view/14381
  32. 10.18653/v1 · doi:10.18653/v1
  33. Diana Perez-Marin and Ismael Pascual-Nieto. 2011. Conversational Agents and Natural Language Interaction: Techniques and Effective Practices. Information Science Reference - Imprint of: IGI Publishing, Hershey, PA.
  34. Nathaniel Persily and Joshua A. Tucker. 2020. Social Media and Democracy: The State of the Field, Prospects for Reform. Cambridge University Press. Google-Books-ID: TgH3DwAAQBAJ.
  35. 10.18653/v1 · doi:10.18653/v1
  36. 10.1109/PASSAT · doi:10.1109/passat
  37. Priyanka Ranade, Aritran Piplai, Sudip Mittal, Anupam Joshi, and Tim Finin. 2021. Generating Fake Cyber Threat Intelligence Using Transformer-Based Models. arXiv:2102.04351 [cs] (June 2021). http://arxiv.org/abs/2102.04351 arXiv:2102.04351. · arXiv
  38. Erin Rand. 2014. Reclaiming Queer: Activist & Academic Rhetorics of Resistance. University of Alabama Press.
  39. Matthew Rimmer. 2013. Patent-Busting: The Public Patent Foundation Gene Patents and the Seed Wars. In The Intellectual Property and Food Project Charles Lawson and Jay Sanderson (Eds.). Routledge.
  40. Karen Sparck Jones. 2004. Language modelling’s generative model: is it rational?Computer Laboratory, University of Cambridge, Cambridge, UK.
  41. William. Stanley Jevons. 1905. The Coal Question: An Inquiry Concerning the Progress of the Nation, and the Probable Exhaustion of Our Coal-mines(3 ed.). Augustus M. Kelley, New York.
  42. Carissa Véliz. 2019. Privacy matters because it empowers us all | Aeon Essays. Aeon (September 2019). https://aeon.co/essays/privacy-matters-because-it-empowers-us-all
  43. 10.5555/2390374.2390377 · doi:10.5555/2390374.2390377
  44. Michael Webb. 2019. The Impact of Artificial Intelligence on the Labor Market. SSRN Scholarly Paper ID 3482150. Social Science Research Network, Rochester, NY. https://papers.ssrn.com/abstract=3482150
  45. Genta Indra Winata, Andrea Madotto, Zhaojiang Lin, Rosanne Liu, Jason Yosinski, and Pascale Fung. 2021. Language Models are Few-shot Multilingual Learners. arXiv:2109.07684 [cs] (September 2021). http://arxiv.org/abs/2109.07684 arXiv:2109.07684. · arXiv

Cited by

See all 776

Metadata

Authors
Weidinger, L., Uesato, J., Rauh, M., Griffin, C., Huang, P.-S., Mellor, J., Glaese, A., Cheng, M., Balle, B., Kasirzadeh, A., Biles, C., Brown, S., Kenton, Z., Hawkins, W., Stepleton, T., Birhane, A., Hendricks, L. A., Rimell, L., Isaac, W., Haas, J., Legassick, S., Irving, G., & Gabriel, I.
Affiliations
  • Google DeepMind (United Kingdom) (GB)
  • California Institute of Technology (US)
  • University of Toronto (CA)
  • University College Dublin (IE)
Venue
2022 ACM Conference on Fairness Accountability and Transparency
Publisher
ACM
Published
2022-06-20
Pages
214-229
OpenAlex
W4283170666
Cited by
764
References
68
Citations by year
2026: 256 · 2025: 228 · 2024: 175 · 2023: 101 · 2022: 3
FWCI
125.64
Type
conference paper
Language
en
Open access
Locations
  • ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion, cc-by)
  • PhilSci-Archive (University of Pittsburgh) (acceptedVersion)
  • Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, other-oa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
Keywords
large language models, risk taxonomy, ethical risks, social risk, responsible innovation, discrimination, hate speech, misinformation, environmental impact, socio-economic impacts, risk mitigation, risk assessment

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Taxonomy of Risks posed by Language Models. https://app.cochat.ai/papers/10.1145/3531146.3533088
The paper
Weidinger, L., Uesato, J., Rauh, M., Griffin, C., Huang, P.-S., Mellor, J., Glaese, A., Cheng, M., Balle, B., Kasirzadeh, A., Biles, C., Brown, S., Kenton, Z., Hawkins, W., Stepleton, T., Birhane, A., Hendricks, L. A., Rimell, L., Isaac, W., . . . Gabriel, I. (2022). Taxonomy of Risks posed by Language Models. 2022 ACM Conference on Fairness Accountability and Transparency. https://doi.org/10.1145/3531146.3533088

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.