We’re thrilled to welcome you to New England NLP 2025 at Yale University on April 11th in New Haven, CT 🎉 nenlp.github.io/spr2025/! Join us for a full day of exciting talks and sparkling discussions with NLP researchers across the New England region and beyond. 👉 Register now

New England NLP 2025 is coming 🎉Join us at Yale!

🚀Excited to share that our paper on LLM evaluation has been accepted to Findings of #NAACL2025! 🎉 Huge thanks to my amazing collaborators Yixin Liu, Jonathan Bragg, and Arman Cohan! 1⃣we discovered that the ranking of evaluation models based on instance-level human

I’ll be presenting ReIFE at #NAACL2025 Poster Session 7 this morning from 09:00 to 10:30 AM! Come by if you're interested in evaluating LLMs as judges! We're also presenting a related work on evaluating automatic LLM benchmarkers in the same session: x.com/mingqi70158/st… —

💡Scientific problem-solving with LLMs needs both domain knowledge + reasoning capabilities. In our new paper, we introduce benchmarks & analytical toolkits to study this. Main takeaways: 1️⃣ Domain knowledge = key bottleneck 2️⃣ In-context knowledge further improves reasoning