🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Join us at USC's Thomas Lord Department of Computer Science! We’re hiring associate and full professors in all areas of computer science. Apply now: cs.usc.edu/about/open-fac… Please share with you communities! USC Viterbi School USC School of Advanced Computing

I will be presenting our work: OATH-Frames, next week at #EMNLP2024 in Computational Social Science and Cultural Analytics 2 (10:30-12pm EST) Thursday 11/14. Please reach out if you want to chat about NLP x Computational Social Science and LLMs for social good applications ✨

Come by Poster Session A tomorrow to hear Sayan Ghosh tell you why your preference eval is probably broken (and how you can fix it!)

My favorite paper at #EMNLP2024: „OATH-Frame: a novel framework to understand, synthesize and characterize large-scale public attitudes towards societal issues through a collaboration between social work experts and LLM“ by Jaspreet Ranjit et al. dill-lab.github.io/oath-frames/

#NLProc can help analyze public attitudes towards homelessness on social media to inform public policy, Jaspreet Ranjit presents at #EMNLP2024 aclanthology.org/2024.emnlp-mai…

Congrats Alexander Spangher (going to NAACL) and co-authors Sebastian Gehrmann Violet Peng on our #EMNLP2024 Outstanding Paper Award Tech At Bloomberg x.com/AlexanderSpang… Also congrats to Johns Hopkins Engineering JHU CLSP Johns Hopkins Data Science and AI Institute colleagues Jason Eisner Benjamin Van Durme Yunmo Chen on their award!

We won an outstanding paper award at #EMNLP2024! So proud of my PhD students Jaspreet Ranjit and Brihi Joshi, the wonderful @rebeccadorn_ and our generous collaborators at USC's School of Social Work, especially Eric Rice. Thanks for making it happen, USC Center for AI in Society!

We have an incredible community at USC NLP 😍

Feeling deeply grateful to have won an outstanding paper award at #EMNLP2024 for our work: OATH-Frames, congrats to my amazing collaborators! Brihi Joshi @rebeccadorn_ Laura, Olga, Jayne, Peichen, Eric Rice Swabha Swayamdipta ✨ Btw, I’m actively looking for internships for summer 2025!

On the horizon for March 31 – April 4, a workshop on The Future of Language Models and Transformers, organized by Sasha Rush and Swabha Swayamdipta. Join us! simons.berkeley.edu/workshops/futu…

Congratulations to the ShowCAIS 2025 Best Doctoral Oral Presentation winners Hannah Murray, Jaspreet Ranjit, and Charles Bickham!!! We are so proud of you 🥳✌️ Check out their abstracts: sites.google.com/usc.edu/showca… @uscviterbi USC Social Work @google PsychArmor

Reasoning about the "why" behind user behavior can improve LLM personas! ✨🧠📈 📝Excited to share our new work: Improving LLM Personas via Rationalization with Psychological Scaffolds 🔗 arxiv.org/abs/2504.17993 🧵 (1/n)

Hallucinations in LLMs are real—and so are the problems with how we measure them 📉 Our latest work questions the generalizability of hallucination detection metrics across tasks, datasets, model sizes, training methods, and decoding strategies 💥 arxiv.org/abs/2504.18114 (1/n)