Celebrating Susan Dumais: Reflections on a Legacy of Research and Collaboration | Plenary Session
Plenary session at the March 14, 2025 “Festschrift” celebrating the career of Susan Dumais. We hear from Susan, who provides a few reflections, as well as two people who helped shape her research and career:…
Steering LLMs for better instruction following
This repository contains the code for the paper “Improving Instruction-Following in Language Models through Activation Steering,” presented at ICLR 2025.
The reality of generative AI in the clinic
UC San Diego Health’s Dr. Christopher Longhurst and UC San Francisco Health’s Dr. Sara Murray explore how generative AI is changing patient care, clinical workflows, and decision-making and how they envision the technology impacting the…
Claimify: Extracting high-quality claims from language model outputs
Claimify, created by Microsoft Research, is a novel LLM-based claim-extraction method that outperforms prior solutions to produce more accurate, comprehensive, and substantiated claims from LLM outputs.