Fateme Hashemi Chaleshtori
@fatemehc.bsky.social
๐ค 339
๐ฅ 226
๐ 10
PhD student at Utah NLP, Mechanistic Interpretability, Trustworthy AI, Human-centered AI
reposted by
Fateme Hashemi Chaleshtori
Ana Marasoviฤ
about 2 months ago
๐๐'๐ง๐ ๐๐๐ง๐๐ฃ๐ ๐ฃ๐๐ฌ ๐๐๐๐ช๐ก๐ฉ๐ฎ ๐ข๐๐ข๐๐๐ง๐จ! KSoC:
utah.peopleadmin.com/postings/190...
(AI broadly) Education + AI: -
utah.peopleadmin.com/postings/189...
-
utah.peopleadmin.com/postings/190...
Computer Vision: -
utah.peopleadmin.com/postings/183...
1
16
10
So thankful for this amazing team and all I learned through the process! Proud of how it all came together๐๐ ๐:
aclanthology.org/2025.emnlp-m...
add a skeleton here at some point
about 2 months ago
0
9
0
reposted by
Fateme Hashemi Chaleshtori
Martin Tutek
about 2 months ago
Very honored to be one out of seven outstanding papers at this years' EMNLP :) Huge thanks to my amazing collaborators
@fatemehc.bsky.social
@anamarasovic.bsky.social
@boknilev.bsky.social
, this would not have been possible without them!
2
22
8
reposted by
Fateme Hashemi Chaleshtori
Martin Tutek
4 months ago
Thrilled that FUR was accepted to
@emnlpmeeting.bsky.social
Main๐ In case you canโt wait so long to hear about it in person, it will also be presented as an oral at
@interplay-workshop.bsky.social
@colmweb.org
๐ฅณ FUR is a parametric test assessing whether CoTs faithfully verbalize latent reasoning.
add a skeleton here at some point
1
13
4
1/ ๐จNEW PAPER: "BriefMe: A Legal NLP Benchmark for Assisting with Legal Briefs", accepted to ACL Findings 2025! We introduce the first benchmark specifically designed to help LLMs assist lawyers in writing legal briefs ๐งโโ๏ธ ๐
arxiv.org/abs/2506.06619
๐๏ธ
huggingface.co/datasets/jw4...
6 months ago
1
7
6
reposted by
Fateme Hashemi Chaleshtori
Martin Tutek
10 months ago
It has been amazing to work with
@fatemehc.bsky.social
,
@anamarasovic.bsky.social
and Yonatan Belinkov on this incredibly important topic. I look forward to further works on the parametric faithfulness route! Codebase (& data):
github.com/technion-cs-...
loading . . .
GitHub - technion-cs-nlp/parametric-faithfulness
Contribute to technion-cs-nlp/parametric-faithfulness development by creating an account on GitHub.
https://github.com/technion-cs-nlp/parametric-faithfulness
0
6
2
you reached the end!!
feeds!
log in