ACL 2024findings1 citations

Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Dataset

Satanu Ghosh, Neal Brodnik, Carolina Frey, Collin Holgate, Tresa Pollock, Samantha Daly, Samuel Carton

Abstract

We explore the ability of GPT-4 to perform ad-hoc schema-based information extraction from scientific literature. We assess specifically whether it can, with a basic one-shot prompting approach over the full text of the included manusciprts, replicate two existing material science datasets, one pertaining to multi-principal element alloys (MPEAs), and one to silicate diffusion. We collaborate with materials scientists to perform a detailed manual error analysis to assess where and why the model struggles to faithfully extract the desired information, and draw on their insights to suggest research directions to address this broadly important task.

BibTeX
@inproceedings{ghosh-etal-2024-toward,
    title = "Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Dataset",
    author = "Ghosh, Satanu  and
      Brodnik, Neal  and
      Frey, Carolina  and
      Holgate, Collin  and
      Pollock, Tresa  and
      Daly, Samantha  and
      Carton, Samuel",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-acl.897/",
    doi = "10.18653/v1/2024.findings-acl.897",
    pages = "15109--15123"
}