@inproceedings{zhang-etal-2025-chemactor,
    title = "{C}hem{A}ctor: Enhancing Automated Extraction of Chemical Synthesis Actions with {LLM}-Generated Data",
    author = "Zhang, Yu  and
      Yu, Ruijie  and
      Tian, Jidong  and
      Zhu, Feng  and
      Liu, Jiapeng  and
      Yang, Xiaokang  and
      Jin, Yaohui  and
      Xu, Yanyan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1183/",
    pages = "24291--24314",
    ISBN = "979-8-89176-251-0",
    abstract = "With the increasing interest in robotic synthesis in the context of organic chemistry, the automated extraction of chemical procedures from literature is critical. However, this task remains challenging due to the inherent ambiguity of chemical language and the high cost of human annotation required for developing reliable computer-aided extraction protocols. Here, we present \textbf{ChemActor}, a fully fine-tuned large language model (LLM), as a chemical executor to convert between unstructured experimental procedures and structured action sequences. We propose a sequential LLM-generated data framework to address the challenges of insufficient and low-quality annotated data. This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input. Additionally, we introduce a novel multi-round LLMs circle review metric, which reflects the model{'}s advanced understanding of chemical experimental procedures. Extensive experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor, augmented by LLM-generated data, achieves state-of-the-art performance, outperforming the baseline model by 10{\%}. The code is available at: https://github.com/Zhanghahah/ChemActor."
}