Amazon Study: LLMs Develop Systemic Sentiment Bias After Memorizing User Profiles

jiqizhixin · x · 2026-07-04

Amazon researchers found that when LLMs memorize user profiles (e.g., single mother vs. wealthy executive), they exhibit systemic bias when judging identical emotional scenarios. High-performance models provide more accurate sentiment interpretations for privileged groups, reinforcing social class disparities in their reasoning and suggestions. The team also released a new dataset to mitigate demographic impacts on models, accompanied by a paper and GitHub.

Original post →

More from Safety

Safety channel →