LLMs for Research
Large language models (LLMs) like ChatGPT have proven to be extremely effective at generating useful responses to a wide variety of user’s questions. However, they often struggle to generate meaningful and accurate responses to questions that are highly specialized, context-dependent, and requiring long-term attention. The goal of this project is to apply LLMs to accelerate technical research and development, particularly in the field of quantum computing, to enhance research productivity and address the limitations of current state-of-the-art models. It will leverage techniques shown to be useful in the academic literature, but applied in the novel setting of highly technical and detailed texts where models frequently struggle, namely quantum computing research. Successful delivery will yield a useful service for researchers at Zapata, as well as a comprehensive application Zapata can demo with prospective clients who are looking to use LLMs for accelerating their R&D cycle.
View Full Project DescriptionAlán Aspuru-Guzik
Zapata Canada
Computer science
Professional, scientific and technical services
University of Toronto
Accelerate