@inproceedings{li-2025-formula,
    title = "Formula-Text Cross-Retrieval: A Benchmarking Study of Dense Embedding Methods for Mathematical Information Retrieval",
    author = "Li, Zichao",
    editor = "Valentino, Marco  and
      Ferreira, Deborah  and
      Thayaparan, Mokanarangan  and
      Ranaldi, Leonardo  and
      Freitas, Andre",
    booktitle = "Proceedings of The 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025)",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.mathnlp-main.9/",
    pages = "124--133",
    ISBN = "979-8-89176-348-7",
    abstract = "Mathematical information retrieval requires understanding the complex relationship between natural language and formulae. This paper presents a benchmarking study on Formula-Text Cross-Retrieval, comparing a sparse baseline (BM25), off-the-shelf dense embeddings (OpenAI, BGE), and a fine-tuned dual-encoder model. Our model, trained with a contrastive objective on the ARQAR dataset, significantly outperforms all baselines, achieving state-of-the-art results. Ablation studies confirm the importance of linearization, a shared-weight architecture, and the Multiple Negatives Ranking loss. The work provides a strong foundation for mathematical NLP applications."
}