Taxonomy of risks posed by language models

Laura Weidinger, Jonathan Uesato, Maribeth Rauh, Conor Griffin, Po-sen Huang, John Mellor, Amelia Glaese, Myra Cheng, Borja Balle, Atoosa Kasirzadeh, Courtney Biles, Sasha Brown, Zac Kenton, Will Hawkins, Tom Stepleton, Abeba Birhane, Lisa Anne Hendricks, Laura Rimell, William Isaac, Julia HaasSean Legassick, Geoffrey Irving, Iason Gabriel

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageEnglish
Title of host publicationFAccT '22
Subtitle of host publication2022 ACM Conference on Fairness, Accountability, and Transparency
ISBN (Print)9781450393522
Publication statusPublished - Sep 2022


  • language models
  • responsible innovation
  • technology risks
  • responsible AI
  • risk assessment


Dive into the research topics of 'Taxonomy of risks posed by language models'. Together they form a unique fingerprint.

Cite this