Mining experimental data from Materials Science literature with Large Language Models

This study is dedicated to evaluating the capabilities of advanced large language models (LLMs) such as GPT-3.5-Turbo, GPT-4, and GPT-4-Turbo in the extraction of structured information from scientific documents within the field of materials science. We introduce a novel methodology for the comparative analysis of intricate material expressions, emphasising the standardisation of chemical formulas to tackle the complexities inherent in materials science information assessment. To this end, we primarily focus on two critical tasks of information extraction: (i) a named entity recognition (NER) of studied materials and physical properties and (ii) a relation extraction (RE) between these entities. The performance of LLMs in executing these tasks is benchmarked against traditional models based on the BERT architecture and rule-based approaches. For NER, LLMs fail to outperform the baseline with zero-shot prompting and exhibit only limited improvement with few-shot prompting. However, for RE, a GPT-3.5-Turbo fine-tuned with the appropriate strategy outperforms all models, including the baseline. Without any fine-tuning, GPT-4 and GPT-4-Turbo display remarkable reasoning and relationship extraction capabilities after being provided with merely a couple of examples, surpassing the baseline. Overall, the results suggest that although LLMs demonstrate relevant reasoning skills in connecting concepts, for tasks requiring extracting complex domain-specific entities like materials, specialised models are currently a better choice.