AdSoLve: Addressing Socio-technical Limitations of LLMs for Medical and Social Computing

Large Language Models (LLMs), like those used in ChatGPT and virtual assistants, are cutting-edge artificial intelligence algorithms trained on massive amounts of text data. They can generate human-like text as well as creative content, translate across languages, and answer questions in an informative way.

However they have known technical limitations such as biases, privacy leaks, poor reasoning and lack of explainability, which raises concerns about their use in critical domains such as healthcare and law.

Our vision is to address socio-technical limitations of LLMs that pose a challenge for their responsible and trustworthy use, considering use cases in legal and medical contexts. 

DERI's Director Prog Greg Slabaugh is part of the team who is working on this project.  Find our more about their workstreams and events here.