Laissez-Faire Harms: Algorithmic Biases in Generative Language Models

[2404.07475] Laissez-Faire Harms: Algorithmic Biases in Generative Language Models Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2404.07475 (cs) [Submitted on 11 Apr 2024 ( v1 ), last revised 16 Apr 2024 (this version, v2)] Title: Laissez-Faire Harms: Algorithmic Biases in Generative Language Models Authors: Evan Shieh , Faye-Marie Vassel , Cassidy Sugimoto , Thema Monroe-White View a PDF of the paper titled Laissez-Faire Harms: Algorithmic Biases in Generative Language Models, by Evan Shieh and 3 other authors View PDF Abstract: The rapid deployment of generative language models (LMs) has raised concerns about social biases affecting the well-being of diverse consumers. The extant literature on generative LMs has primarily examined bias via explicit identity prompting. However, prior research on bias in earlier language-based technology platforms, including search engines, has shown that discrimination can occur even when identity terms are not specified explicitly. Studies of bias in LM responses to open-ended prompts (where identity classifications are left unspecified) are lacking and have not yet been grounded in end-consumer harms. Here, we advance studies of generative LM bias by considering a broader set of natural use cases via open-ended prompting. In this "laissez-faire" setting, we find that synthetically generated texts from five of the most pervasive LMs (ChatGPT3.5, ChatGPT4, Claude2.0, Llama2, and PaLM2) perpetuate harms of omission, subordination, and stereotyping for minoritized individuals with intersectional race, gender, and/or sexual orientation identities (AI/AN, Asian, Black, Latine, MENA, NH/PI, Female, Non-binary, Queer). We find widespread evidence of bias to an extent that such individuals are hundreds to thousands of times more likely to encounter LM-generated outputs that portray their identities in a subordinated manner compared to representative or empowering portrayals. We also document a prevalence of stereotypes (e.g. perpetual foreigner) in LM-generated outputs that are known to trigger psychological harms that disproportionately affect minoritized individuals. These include stereotype threat, which leads to impaired cognitive performance and increased negative self-perception. Our findings highlight the urgent need to protect consumers from discriminatory harms caused by language models and invest in critical AI education programs tailored towards empowering diverse consumers. Comments: 16 pages (43 if including supplementals), 8 figures (23 if including supplementals) Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG) Cite as: arXiv:2404.07475 [cs.CL] (or arXiv:2404.07475v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2404.07475 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Nat Commun 17, 1243 (2026) Related DOI : https://doi.org/10.1038/s41467-025-68004-9 Focus to learn more DOI(s) linking to related resources Submission history From: Evan Shieh [ view email ] [v1] Thu, 11 Apr 2024 05:09:03 UTC (1,953 KB) [v2] Tue, 16 Apr 2024 04:07:42 UTC (1,953 KB) Full-text links: Access Paper: View a PDF of the paper titled Laissez-Faire Harms: Algorithmic Biases in Generative Language Models, by Evan Shieh and 3 other authors View PDF view license Current browse context: cs.CL < prev | next > new | recent | 2024-04 Change to browse by: cs cs.AI cs.CY cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Laissez-Faire Harms: Algorithmic Biases in Generative Language Models#189183
• Laissez-Faire Harms: Algorithmic Biases in Generative Language Models#189083
• Laissez-Faire Harms: Algorithmic Biases in Generative Language Models#189033
• Harmfulness Propagation Dynamics: Layer-wise Trajectories of Adversarial Intent in Large Language Models#1071316
• LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spike#463878