Daniel Arnould
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
CA-BED is a novel framework that improves LLM performance in interactive question-answering by integrating Bayesian Experimental Design to strategically select questions that maximize information gain over multiple conversational turns.
CA-BED is a novel framework that improves LLM performance in interactive question-answering by integrating Bayesian Experimental Design to strategically select questions that maximize information gain over multiple conversational turns.
Papers
CA-BED: Conversation-Aware Bayesian Experimental Design
Daniel Arnould, Rashad Aziz, Zixuan Kang, Tanav Changal +4 more
CA-BED is a novel framework that improves LLM performance in interactive question-answering by integrating Bayesian Experimental Design to strategically select questions that maximize information gain…