at://
/
app.bsky.feed.post
/
3ljppn32ihs2k
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
Our findings stress the importance of leveraging the distributional output of LLM-as-a-judge, as opposed to using the text interface alone. Check out the full paper at arxiv.org/pdf/2503.03064!
Mar 6, 2025
arxiv.org
Victor Wang
