MSR: Structural Reasoning Improves Molecular Understanding of LLM

Overview

Large language models struggle with molecular structural reasoning despite their advanced capabilities. We introduce the Molecular Structural Reasoning (MSR) framework to enhance LLM performance by explicitly incorporating the key structural features. We present two distinct approaches for scenarios where target molecules are identified or unidentified, validating improvements through comprehensive testing on molecular understanding tasks.

BibTeX

@inproceedings{jang-etal-2025-structural,
  title = "Structural Reasoning Improves Molecular Understanding of {LLM}",
  author = "Jang, Yunhui  and
    Kim, Jaehyung  and
    Ahn, Sungsoo",
  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://aclanthology.org/2025.acl-long.1023/",
  doi = "10.18653/v1/2025.acl-long.1023",
  pages = "21016--21036",
  ISBN = "979-8-89176-251-0"}