@inproceedings{cao-etal-2024-presto,
    title = "{PRESTO}: Progressive Pretraining Enhances Synthetic Chemistry Outcomes",
    author = "Cao, He  and
      Shao, Yanjun  and
      Liu, Zhiyuan  and
      Liu, Zijing  and
      Tang, Xiangru  and
      Yao, Yuan  and
      Li, Yu",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.findings-emnlp.597/",
    doi = "10.18653/v1/2024.findings-emnlp.597",
    pages = "10197--10224",
    abstract = "Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific disciplines. These advancements encourage the investigation of molecule-text modeling within synthetic chemistry, a field dedicated to designing and conducting chemical reactions to synthesize new compounds with desired properties and applications. Current approaches, however, often neglect the critical role of multi-molecule graph interaction in understanding chemical reactions, leading to suboptimal performance in synthetic chemistry tasks. This study introduces PRESTO (Progressive Pretraining Enhances Synthetic Chemistry Outcomes), a new framework that bridges the molecule-text modality gap by integrating a comprehensive benchmark of pretraining strategies and dataset configurations. It progressively improves multimodal LLMs through cross-modal alignment and multi-graph understanding. Our extensive experiments demonstrate that PRESTO offers competitive results in downstream synthetic chemistry tasks. The code can be found at https://github.com/IDEA-XL/PRESTO."
}