LLM Digest
Subscribe

Story

arxiv_cs_cl · Nov 16, 2026 · paper

Source brief

A Crowd-Audited Atlas of Implicit Bias in LLM-Powered Agents

arxiv.orgNov 16, 2026
original source linked

In brief

Prior work has shown that large language models (LLMs) express implicit biases in high-publicity, one-off decision scenarios such as hiring and intelligence assessment. However, as people increasingly employ autonomous, LLM-powered AI agents that make decisions on their behalf in

Feed lens
agent

Continue reading

Read the original at arxiv.org →Open in live feedRead that day’s brief

Earlier in this thread 4 items