The ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) 2025 is being hosted in Athens, Greece from June 23 - 26. We’re excited to share all the work from SAIL that’s being presented, and you’ll find links to the papers below. Feel free to reach out to the contact authors directly to learn more about the work that’s happening at Stanford!
List of Accepted Papers
Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers
Contact: jlcmoore@stanford.edu
Links: Paper | Blog Post | Website
Keywords: mental health, therapy, large language models, chatbots
From tools to thieves: Measuring and understanding public perceptions of AI through crowdsourced metaphors
Contact: myra1@stanford.edu
Links: Paper
Keywords: metaphors, perceptions of ai, demographic differences in perceptions, public perceptions
Identities are not Interchangeable: The Problem of Overgeneralization in Fair Machine Learning
Contact: angelina.wang@stanford.edu
Links: Paper
Keywords: machine learning fairness, discrimination, context specificity, social identities
Measuring Machine Learning Harms from Stereotypes Requires Understanding Who Is Harmed by Which Errors in What Ways
Contact: angelina.wang@stanford.edu
Links: Paper
Keywords: stereotypes, machine learning fairness, harms from biases
Not Like Us, Hunty: Measuring Perceptions and Behavioral Effects of Minoritized Anthropomorphic Cues in LLMs
Contact: dchechel@andrew.cmu.edu
Links: Paper
Keywords: natural language processing, linguistics, large language models, sociolect, user perception, user behavior, reliance, anthropomorphization, african american english, queer slang
We look forward to seeing you at FAccT!