Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • NEWS AND VIEWS

LLMs produce racist output when prompted in African American English

Large language models (LLMs) are becoming less overtly racist, but respond negatively to text in African American English. Such ‘covert’ racism could harm speakers of this dialect when LLMs are used for decision-making.
By
  1. Su Lin Blodgett

    1. Su Lin Blodgett is at Microsoft Research Montreal, Montreal, Quebec H2S 3J9, Canada.

  2. Zeerak Talat

    1. Zeerak Talat is at the Mohamed Bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, United Arab Emirates.

Access through your institution
Buy or subscribe

Large language models (LLMs) are increasingly being used in a wide range of applications, from summarizing news articles to serving as study assistants in classroom settings1, but emerging evidence suggests that language technologies can behave unjustly. Writing in Nature, Hofmann et al.2 explore the racial prejudices that LLMs exhibit on the basis of dialect.

Access options

Access through your institution

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Nature 633, 40-41 (2024)

doi: https://doi.org/10.1038/d41586-024-02527-x

References

  1. Wang, S. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2403.18105 (2024).

  2. Hofmann, V., Kalluri, P. R., Jurafsky, D. & King, S. Nature 633, 147–154 (2024).

    Article  Google Scholar 

  3. Hutchinson, B. et al. In Proc. 58th Ann. Mtg Assoc. Comput. Linguist. (eds Jurafsky, D., Chai, J., Schluter, N. & Tetreault, J.) 5491–5501 (Assoc. Comput. Linguist., 2020).

    Google Scholar 

  4. Abid, A., Farooqi, M. & Zou, J. In AIES ’21: Proc. 2021 AAAI/ACM Conf. AI, Ethics, and Society 298–306 (2021).

  5. Green, L. J. African American English: a Linguistic Introduction (Cambridge Univ. Press, 2002).

    Google Scholar 

  6. Craft, J. T., Wright, K. E., Weissler, R. E. & Queen, R. M. Annu. Rev. Linguist. 6, 389–407 (2020).

    Article  Google Scholar 

  7. Koenecke, A. et al. Proc. Natl Acad. Sci. USA 117, 7684–7689 (2020).

    Article  PubMed  Google Scholar 

  8. Groenwold, S. et al. In Proc. 2020 Proc. Conf. Empir. Meth. Nat. Lang. Process. (eds Webber, B., Cohn, T., He, Y. & Liu, Y.) 5877–5883 (Assoc. Comput. Linguist., 2020).

    Google Scholar 

Download references

Competing Interests

The authors declare no competing interests.

Subjects

Latest on:

Nature Careers

Jobs

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing

Search

Advanced search

Quick links