iiinova — where your digital self keeps evolving

Shivani Kumar

@shivanikumar.bsky.social

Postdoc @ University of Michigan | PhD from LCS2, IIITDelhi | Working in Computational Social Science #NLProc More info: kumarshivani.com

Posts Replies Media

Reposted by Shivani Kumar

David Jurgens @davidjurgens.bsky.social · 16/04/2026

Great showing by Michigan NLP folks (and alumni) at Midwest Speech and Language Days this year. nlp.cs.illinois.edu/msld.html it's fun seeing papers from *ACL, NeurIPS, ICLR, COLM, Interspeech, and more all together. Lots of interesting work everywhere!!

0102

Reposted by Shivani Kumar

Jacy Reese Anthis @jacyanthis.bsky.social · 30/07/2025

Morality in AI is often oversimplified. @davidjurgens.bsky.social and @shivanikumar.bsky.social kick off the "Human-Centred NLP" orals #ACL2025NLP with UniMoral, a huge dataset of moral scenario ratings in 6 languages! They find LLMs fail to simulated human moral decisions. bsky.app/profile/shiv...

David Jurgens gives talk with slides of country map

1102

Shivani Kumar @shivanikumar.bsky.social · 01/03/2025

Can AI grasp how humans across cultures reason through moral dilemmas? ✨Meet UniMoral-a unique multilingual dataset merging psychology & NLP to model moral reasoning as a pipeline. It enables LLMs to reason about decisions and their ethical implications across languages. Thread🧵(1/n)

130