Speaker: Danqi Chen, Princeton University
Talk Title: From RAG to Long-context Models: Benchmarks and Model Developments
Date: Friday, February 28, 2025 - 1:30 - 2:30 PM EST (North American Eastern Standard Time)
Abstract: Retrieval-augmented generation (RAG) is crucial for enhancing language models by incorporating external knowledge, enabling more accurate and up-to-date responses. Effective RAG systems require long-context models that can efficiently process and synthesize retrieved information. In this talk, I will present our recent research on: (1) benchmarking the long-context capabilities of LLMs, including RAG as a core application (ALCE, HELMET, BRIGHT) and the ability to follow structured procedures and generate long, coherent outputs (LongProc); and (2) developing long-context models through careful data engineering and evaluation (ProLong), which achieves state-of-the-art performance with significantly lower computational cost than industry standards. I will share insights from these studies and discuss key challenges and open research questions in this space.
Bio: Danqi Chen is an Assistant Professor of Computer Science at Princeton University and co-leads the Princeton NLP group. She is also an Associate Director of Princeton Language and Intelligence. Her recent research focuses on training, adapting, and understanding large language models, especially with the goal of making them more accessible to academia. Before joining Princeton, Danqi was a visiting scientist at Facebook AI Research. She received her Ph.D. from Stanford University (2018) and her B.E. from Tsinghua University (2012), both in Computer Science. Her research was recognized by a Sloan Fellowship, an NSF CAREER award, a Samsung AI Researcher of the Year award, and outstanding paper awards from ACL and EMNLP.
Zoom Access: Zoom Link and reach out to Hamed Zamani or Dan Parker for the passcode.