Towards Trustworthy Large Language Models
Oluwasanmi Koyejo, Bo Li
Abstract
Large Language models are among the most exciting technologies developed in the last few years. While the model's capabilities continue to improve, researchers, practitioners, and the general public are increasingly aware of some of its shortcomings. What will it take to build trustworthy large language models?
Topics & Concepts
TrustworthinessComputer scienceData scienceLanguage modelComputer securityArtificial intelligenceTopic Modeling