Congratulations to our PhD students Hita K Ro E p. sampson for being awarded the U.S. National Science Foundation Graduate Research Fellowship! We are so proud of you!! 💫🪩👩🏾‍💻👩🏽‍💻🧑🏾‍💻

I’ve arrived at #CHI2024🌺!! I’m super excited to present our paper on how AI-assisted reading interfaces should be designed to help patients better understand their medical notes. Come check out the presentation on Wednesday May 15th at 11:30AM 🩺📑

One of the coolest parts of my job is I get to teach classes like this one---my new research seminar on Interactive Reading 📖✨ Open to students at Penn Computer and Information Science and the university broadly. Check out the teaser for info!

🚨 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

Excited for #CHI2025 🌸(my first!) & looking forward to connecting with folks building culturally sensitive, scalable, policy-focused AI for Health. Neil Sehgal & Hita K present our ongoing work on designing AI for adolescent mental health in India: dl.acm.org/doi/10.1145/37…

🚨 New preprint on AI persuasion and public health 🚨 A 3-min conversation with GPT-4o nudged HPV-vax-hesitant parents (who obv knew it was AI & consented!)—BUT reading standard public-health material still outperformed chatbots in impact and longevity. Details below 👇

What if survey-derived rubrics 📋 graded ChatGPT instead of vibes? We benchmark LLMs & deep research systems across 75 research fields 🩺🧬🦾⚗️🏛️🎭💹: Perplexity deep research wins > 82% of head-to-heads vs the next best! w/ Li S. Yifei, Chaitanya Malaviya, and Mark Yatskar