Domain-specific ChatBots for Science using Embeddings
This addresses the need for rigorous and sourced chatbots in science domains, but it is incremental as it combines existing methods and tools.
The paper tackled the problem of applying large language models (LLMs) to physical science research by developing a domain-specific chatbot that uses text and image embeddings to provide contextual information, confirming that LLMs are suitable for accelerating scientific research.
Large language models (LLMs) have emerged as powerful machine-learning systems capable of handling a myriad of tasks. Tuned versions of these systems have been turned into chatbots that can respond to user queries on a vast diversity of topics, providing informative and creative replies. However, their application to physical science research remains limited owing to their incomplete knowledge in these areas, contrasted with the needs of rigor and sourcing in science domains. Here, we demonstrate how existing methods and software tools can be easily combined to yield a domain-specific chatbot. The system ingests scientific documents in existing formats, and uses text embedding lookup to provide the LLM with domain-specific contextual information when composing its reply. We similarly demonstrate that existing image embedding methods can be used for search and retrieval across publication figures. These results confirm that LLMs are already suitable for use by physical scientists in accelerating their research efforts.