Dynamic In-context Learning with Conversational Models for Data Extraction and Materials Property Prediction
This work addresses a data gap in materials science, particularly for rapidly evolving properties like 2D material thicknesses, by providing an efficient tool for autonomous database generation, though it is incremental as it builds on existing LLM methods.
The paper tackles the challenge of ensuring data trustworthiness in extracting material property data from unstructured scholarly papers by introducing PropertyExtractor, a tool that uses conversational LLMs with dynamic in-context learning, achieving precision and recall over 95% and an error rate of about 9% in tests.
The advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that leverages advanced conversational LLMs like Google gemini-pro and OpenAI gpt-4, blends zero-shot with few-shot in-context learning, and employs engineered prompts for the dynamic refinement of structured information hierarchies - enabling autonomous, efficient, scalable, and accurate identification, extraction, and verification of material property data. Our tests on material data demonstrate precision and recall that exceed 95\% with an error rate of approximately 9%, highlighting the effectiveness and versatility of the toolkit. Finally, databases for 2D material thicknesses, a critical parameter for device integration, and energy bandgap values are developed using PropertyExtractor. Specifically for the thickness database, the rapid evolution of the field has outpaced both experimental measurements and computational methods, creating a significant data gap. Our work addresses this gap and showcases the potential of PropertyExtractor as a reliable and efficient tool for the autonomous generation of various material property databases, advancing the field.