AstraZeneca's Research Assistant: An LLM-Based System for R&D
AstraZeneca has rolled out a new tool called Research Assistant, which uses LLM technology to support scientists and clinicians with biomedical research. This system has a chat-like interface and pulls together information from various sources like scientific articles, knowledge graphs, chemistry databases, clinical trials, and more. It offers a quick response feature for simple questions and a detailed mode for complex inquiries. Users can verify the information since answers are backed by sourced evidence. Additionally, a technical note outlines the system's design and findings from its extensive use to improve R&D processes at AstraZeneca. This development is detailed in a paper on arXiv in the Computer Science > Artificial Intelligence section.
Key facts
- AstraZeneca developed Research Assistant, an internal LLM-based system.
- The system helps scientists and clinicians explore biomedical questions.
- It integrates evidence from scientific literature, knowledge graphs, chemistry, clinical trials, safety resources, expression data, and internal experimental systems.
- It offers a fast mode for direct question answering and a multi-step mode for complex tasks.
- Responses are grounded in retrieved evidence and linked to original sources.
- The technical note outlines system architecture, design choices, and lessons learned.
- The system is deployed at scale to support day-to-day R&D workflows.
- The paper is available on arXiv under Computer Science > Artificial Intelligence.
Entities
Institutions
- AstraZeneca
- arXiv