@inproceedings{ha-etal-2025-mv,
    title = "{MV}-{CLAM}: Multi-View Molecular Interpretation with Cross-Modal Projection via Language Model",
    author = "Ha, Sumin  and
      Kim, Jun Hyeong  and
      Piao, Yinhua  and
      Cho, Changyun  and
      Kim, Sun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.1174/",
    doi = "10.18653/v1/2025.findings-emnlp.1174",
    pages = "21528--21549",
    ISBN = "979-8-89176-335-7",
    abstract = {Deciphering molecular meaning in chemistry and biomedicine depends on context {---} a capability that large language models (LLMs) can enhance by aligning molecular structures with language. However, existing molecule-text models ignore complementary information in different molecular views and rely on single-view representations, limiting molecule structural understanding. Moreover, na{\"i}ve multi-view alignment strategies face two challenges: (1) the aligned spaces differ across views due to inconsistent molecule-text mappings, and (2) existing loss objectives fail to preserve complementary information necessary for finegrained alignment. To enhance LLM{'}s ability to understand molecular structure, we propose MV-CLAM, a novel framework that aligns multi-view molecular representations into a unified textual space using a multi-querying transformer (MQ-Former). Our approach ensures cross-view consistency while the proposed token-level contrastive loss preserves diverse molecular features across textual queries. MV-CLAM enhances molecular reasoning, improving retrieval and captioning accuracy. The source code of MV-CLAM is available in https://github.com/sumin124/mv-clam.}
}