Events
CILVR Seminar: Diverse Retrieval and Generation in LLMs for Comprehensive Answers
Speaker: Eunsol Choi (NYU)
Location:
60 Fifth Avenue, Room 7th floor open space
Videoconference link:
https://nyu.zoom.us/j/96095183843
Date: Wednesday, April 15, 2026
Real-world user queries often contain questions that admit a wide range of valid answers without a single ground truth. However, large language models (LLMs) often struggle to generate diverse and comprehensive responses. In this talk, we will discuss two paths towards this goal, (1) retrieving a diverse set of documents and (2) sampling a broader range of responses from LLMs. First, I will quantify the limitations of existing dense retrievers that rely on a single query vector, demonstrating how models struggle when the target document set exhibits contains dissimilar targets. To address this, we explore two approaches: autoregressively generating multiple query embeddings and introducing an iterative framework that generates new query embedding based on earlier retrieval outputs. Second, I will discuss inference strategies to sample diverse outputs from LLMs. Prompting LLMs to sequentially generate a diverse set of answers works well for simpler factoid queries, but is less effective for more complex queries. We further explore merging outputs from multiple LLMs, showing its potential and challenges. I will conclude by discussing a multi-turn agentic framework interleaving retrieval and generation from LLMs to craft a comprehensive answer.
Bio: Eunsol Choi is an assistant professor of computer science and data science at New York University. Her research spans natural language processing and machine learning, with a focus on interpreting and reasoning about text in dynamic real-world contexts. Prior to joining NYU, she was an assistant professor at the University of Texas at Austin and a visiting researcher at Google. She holds a Ph.D. in computer science and engineering from the University of Washington. She is a recipient of a Facebook research fellowship, Google faculty research award, Sony faculty award, NSF CAREER award and an outstanding paper award at EMNLP.