Swabha
@swabhs.bsky.social
π€ 2707
π₯ 200
π 5
Assistant Professor of CS, University of Southern California. NLP / ML.
reposted by
Swabha
Brihi Joshi
9 months ago
Reasoning about the "why" behind user behavior can improve LLM personas! β¨π§ π πExcited to share our new work: Improving LLM Personas via Rationalization with Psychological Scaffolds π
arxiv.org/abs/2504.17993
π§΅ (1/n)
1
14
5
reposted by
Swabha
Brihi Joshi
9 months ago
π So fun to collaborate with amazing folks at USC (Xiang Ren,
@swabhs.bsky.social
) and Apple (Rik Koncel-Kedziorski, Tim Paek) on this work! π€π‘π£ Excited to finally share thisβlet us know what you think! ππ½β¨π More details in our draft here:
arxiv.org/abs/2504.17993
(8/n)
loading . . .
Improving LLM Personas via Rationalization with Psychological Scaffolds
Language models prompted with a user description or persona can predict a user's preferences and opinions, but existing approaches to building personas -- based solely on a user's demographic attribut...
https://arxiv.org/abs/2504.17993
0
2
1
reposted by
Swabha
Michael Saxon
about 1 year ago
#socalnlp
is the biggest it's ever been in 2024! We have 3 poster sessions up from 2! How many years until it's a two-day event?? π€―
1
26
3
reposted by
Swabha
Jessy Li
about 1 year ago
We at UT Linguistics are hiring for π₯ 2 faculty positions in Computational Linguistics! Assistant or Associate professors, deadline Dec 1. UT has a super vibrant comp ling &
#nlp
community!! Apply here π
apply.interfolio.com/158280
0
12
8
And we're having a great time at
#EMNLP2024
, come talk to us!
add a skeleton here at some point
about 1 year ago
0
15
2
#EMNLP2024
has been a treat so far! Of course it doesn't hurt to win an outstanding paper award with my incredible PhD students Jaspreet Ranjit and
@brihi.bsky.social
and our wonderful collaborators at USC π Paper:
dill-lab.github.io/oath-frames/
about 1 year ago
0
17
2
Hoping against hope that bluesky will be a breath of fresh airπ€Bit much?
over 2 years ago
0
4
0
you reached the end!!
feeds!
log in