
Sunny Rai
@snyrai_
Postdoc @ CIS, University of Pennsylvania. Consultant @ The World Bank. PhD, University of Delhi. #CulturalNLP #MentalHealth #Alignment
ID: 1645929303710875656
https://raisunny.com/ 11-04-2023 23:18:54
76 Tweet
188 Followers
676 Following

fresh audio product: • Neil Sehgal on the durability of slaveholder wealth, via a look at Congress • Emily Jashinsky <Emily Jashinsky> with a conservative’s view of the election • Melissa Lyon on the effects of teachers’ strikes leftbusinessobserver.com/Radio.html#S24…


We're hiring a postdoc Penn to advance data science methods for behavioral health and psychology! Full details here: bit.ly/penn_postdoc_n… You will work with an amazing interdisciplinary team Penn Engineering AI World Well-Being Prj Penn LDI Penn Center for Health Incentives+Behavioral Econ Penn Med Transformation & Innovation Please apply / RT!


🚨 LLMs must grasp implied language to reason about emotions, social cues, etc. Our Google DeepMind paper presents the Implied NLI dataset. Targeting social norms 🌎 and conversational dynamics 💬, we enhance LLM understanding of real-world implication! arxiv.org/abs/2501.07719


I'll be giving a talk at UC Berkeley on February 12th. Join me! UCBerkeley Psychology psychology.berkeley.edu/events/thomas-…


How can we ensure AI systems stay safe and aligned in the context of long-term personal interaction with AI agents? New research with Hannah Rose Kirk, summerfieldlab @summerfieldlab.bsky.social , Bertie Vidgen & Scott Hale aims to answer this question!








Thrilled to share that our work has received the Outstanding Paper Award C3NLP #NAACL2025! 🎉 Huge congratulations to Sunny Rai & Khushi Shelat for leading this collaborative effort, and thanks to Jeffrey (Young-Min) Cho for delivering an amazing talk on behalf of his co-authors! 🙌🏽



Thrilled to share that our work has received the Outstanding Paper Award C3NLP #NAACL2025! 🎉 Jeffrey (Young-Min) Cho Khushi Shelat Sharath Chandra Guntuku

If you are working on AI agents, consider submitting here! It is non archival and an excellent opportunity to receive feedback and showcase your work Conference on Language Modeling