Dynamic In-context Learning with Conversational Models for Data Extraction and Materials Property Prediction

TL;DR

This paper presents PropertyExtractor, an open-source conversational LLM-based tool that accurately extracts and verifies material property data from scholarly papers, addressing data trustworthiness and creating valuable property databases.

Contribution

The paper introduces PropertyExtractor, a novel tool combining advanced conversational LLMs, in-context learning, and prompt engineering for autonomous material data extraction and verification.

Findings

Achieves over 95% precision and recall in data extraction.

Effectively creates databases for 2D material thicknesses and energy bandgaps.

Demonstrates the tool's scalability and accuracy in material data curation.

Abstract

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.