at://
/
app.bsky.feed.post
/
3mcv2dgyg622h
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
2/ We study implicit biases via a word association task: the model assigns demographic labels to names or professions (e.g., “engineer → ?”, “Jack → ?”). Inspired by prior work on implicit associations in LLMs (e.g., Xuechunzi Bai et al., 2025).
4mo
Zhengyang Shan
