@inproceedings{koh-etal-2026-jamendo,
    title = "Jamendo-{MT}-{QA}: A Benchmark for Multi-Track Comparative Music Question Answering",
    author = "Koh, Junyoung  and
      Lee, Jaeyun  and
      Kim, Soo Yong  and
      Choi, Gyu Hyeong  and
      Koh, Jung In  and
      Phillips, Jordan  and
      Lee, Yeonjin  and
      Song, Min",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.125/",
    pages = "2612--2631",
    ISBN = "979-8-89176-395-1",
    abstract = "Recent work on music question answering (Music-QA) has primarily focused on single-track understanding, where models answer questions about an individual audio clip using its tags, captions, or metadata. However, listeners often describe music in comparative terms, and existing benchmarks do not systematically evaluate reasoning across multiple tracks. Building on the Jamendo-QA dataset, we introduce Jamendo-MT-QA, a dataset and benchmark for multi-track comparative question answering. From Creative Commons-licensed tracks on Jamendo, we construct 36,519 comparative QA items over 12,173 track pairs, with each pair yielding three question types: yes/no, short-answer, and sentence-level questions. We describe an LLM-assisted pipeline for generating and filtering comparative questions, and benchmark representative audio-language models using both automatic metrics and LLM-as-a-Judge evaluation."
}