LightNews LightNews
lee-messi.bsky.social
@lee-messi.bsky.social
16 followers 23 following 9 posts
Posts Replies Media Videos
Reposted
calvinklai.bsky.social
🚨New Paper w/ @joelleforestier.bsky.social at JEP: General!🚨 We conducted 2 mega-experiments totaling over 28,000 participants and 50 conditions. We wanted to find the most effective interventions to reduce implicit weight prejudice across 5 implicit measures. 🧵

osf.io/preprints/ps...
April 9, 2025 at 2:32 PM
Reposted
calvinklai.bsky.social
"Implicit" bias + AI research often studies biased outputs. As us psychologists know though, behavior's not the same as process. A model trained on a racist site would show bias, but wouldn't be "implicit"! To study & find biased processing, @lee-messi.bsky.social & I used new reasoning models.
lee-messi.bsky.social lee-messi.bsky.social @lee-messi.bsky.social · Mar 17
In a new paper w/ @calvinklai.bsky.social, I find that OpenAI’s latest reasoning model (o3-mini) exhibits implicit bias-like patterns. What’s exciting about reasoning models is the ability to unpack bias in how models *process* information, rather than just seeing bias in *outputs*. (1/10):
Academic paper header and abstract for "Implicit Bias-Like Patterns in Reasoning Models" by authors Messi H.J. Lee (Washington University in St. Louis) and Calvin K. Lai (Rutgers University), dated March 17, 2025. The abstract explains research on implicit bias-like patterns in AI reasoning models, introducing a method called the Reasoning Model Implicit Association Test (RM-IAT). Their findings show that reasoning models require more computational tokens when processing association-incompatible information versus association-compatible information, suggesting AI systems exhibit processing patterns analogous to human implicit bias.
March 17, 2025 at 4:52 PM
lee-messi.bsky.social
In a new paper w/ @calvinklai.bsky.social, I find that OpenAI’s latest reasoning model (o3-mini) exhibits implicit bias-like patterns. What’s exciting about reasoning models is the ability to unpack bias in how models *process* information, rather than just seeing bias in *outputs*. (1/10):
Academic paper header and abstract for "Implicit Bias-Like Patterns in Reasoning Models" by authors Messi H.J. Lee (Washington University in St. Louis) and Calvin K. Lai (Rutgers University), dated March 17, 2025. The abstract explains research on implicit bias-like patterns in AI reasoning models, introducing a method called the Reasoning Model Implicit Association Test (RM-IAT). Their findings show that reasoning models require more computational tokens when processing association-incompatible information versus association-compatible information, suggesting AI systems exhibit processing patterns analogous to human implicit bias.
March 17, 2025 at 2:23 PM