LLM-based MOFs Synthesis Condition Extraction using Few-Shot Demonstrations

TL;DR

This paper introduces a few-shot learning approach using large language models to extract MOF synthesis conditions from literature, significantly improving accuracy over zero-shot methods and aiding material design.

Contribution

It presents a novel human-AI interactive data curation method and an information retrieval algorithm for effective few-shot demonstration selection in MOF synthesis extraction.

Findings

Few-shot LLMs outperform zero-shot and baseline methods.

Lab-synthesized materials guided by LLM achieve over 91.1% high-quality MOFs.

Method validated across three datasets with significant performance gains.

Abstract

The extraction of Metal-Organic Frameworks (MOFs) synthesis route from literature has been crucial for the logical MOFs design with desirable functionality. The recent advent of large language models (LLMs) provides disruptively new solution to this long-standing problem. While the latest researches mostly stick to primitive zero-shot LLMs lacking specialized material knowledge, we introduce in this work the few-shot LLM in-context learning paradigm. First, a human-AI interactive data curation approach is proposed to secure high-quality demonstrations. Second, an information retrieval algorithm is applied to pick and quantify few-shot demonstrations for each extraction. Over three datasets randomly sampled from nearly 90,000 well-defined MOFs, we conduct triple evaluations to validate our method. The synthesis extraction, structure inference, and material design performance of the proposed few-shot LLMs all significantly outplay zero-shot LLM and baseline methods. The lab-synthesized material guided by LLM surpasses 91.1% high-quality MOFs of the same class reported in the literature, on the key physical property of specific surface area.