Large Language Models for Scientific Synthesis, Inference and Explanation
This work addresses the challenge of accelerating scientific discovery for researchers by integrating LLMs with conventional machine learning, though it appears incremental as it builds on existing LLM capabilities.
The authors tackled the problem of applying large language models (LLMs) to natural science by developing a method for scientific synthesis, inference, and explanation, resulting in a system that outperforms state-of-the-art methods on benchmark tasks for predicting molecular properties.
Large language models are a form of artificial intelligence systems whose primary knowledge consists of the statistical patterns, semantic relationships, and syntactical structures of language1. Despite their limited forms of "knowledge", these systems are adept at numerous complex tasks including creative writing, storytelling, translation, question-answering, summarization, and computer code generation. However, they have yet to demonstrate advanced applications in natural science. Here we show how large language models can perform scientific synthesis, inference, and explanation. We present a method for using general-purpose large language models to make inferences from scientific datasets of the form usually associated with special-purpose machine learning algorithms. We show that the large language model can augment this "knowledge" by synthesizing from the scientific literature. When a conventional machine learning system is augmented with this synthesized and inferred knowledge it can outperform the current state of the art across a range of benchmark tasks for predicting molecular properties. This approach has the further advantage that the large language model can explain the machine learning system's predictions. We anticipate that our framework will open new avenues for AI to accelerate the pace of scientific discovery.