@inproceedings{phi-etal-2025-hybrid,
    title = "A Hybrid {LLM} and Supervised Model Pipeline for Polymer Property Extraction from Tables in Scientific Literature",
    author = "Phi, Van-Thuy  and
      Do, Dinh-Truong  and
      Trieu, Hoang-An  and
      Matsumoto, Yuji",
    editor = "Accomazzi, Alberto  and
      Ghosal, Tirthankar  and
      Grezes, Felix  and
      Lockhart, Kelly",
    booktitle = "Proceedings of the Third Workshop for Artificial Intelligence for Scientific Publications",
    month = dec,
    year = "2025",
    address = "Mumbai, India and virtual",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.wasp-main.11/",
    pages = "94--102",
    ISBN = "979-8-89176-310-4",
    abstract = "Extracting structured information from tables in scientific literature is a critical yet challenging task for building domain-specific knowledge bases. This paper addresses extraction of 5-ary polymer property tuples: (POLYMER, PROP{\_}NAME, PROP{\_}VALUE, CONDITION, CHAR{\_}METHOD). We introduce and systematically compare two distinct methodologies: (1) a novel two-stage Hybrid Pipeline that first utilizes Large Language Models (LLMs) for table-to-text conversion, which is then processed by specialized text-based extraction models; and (2) an end-to-end Direct LLM Extraction approach. To evaluate these methods, we employ a systematic, domain-aligned evaluation setup based on the expert-curated PoLyInfo database. Our results demonstrate the clear superiority of the hybrid pipeline. When using Claude Sonnet 4.5 for the linearization stage, the pipeline achieves a score of 67.92{\%} F1@PoLyInfo, significantly outperforming the best direct LLM extraction approach (Claude Sonnet 4.5 at 56.66{\%}). This work establishes the effectiveness of a hybrid architecture that combines the generative strengths of LLMs with the precision of specialized supervised models for structured data extraction."
}