{"ID":2874074,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.04744","arxiv_id":"2509.04744","title":"WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning","abstract":"Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in the multimodal symbolic music domain remain largely unexplored. We introduce WildScore, the first in-the-wild multimodal symbolic music reasoning and analysis benchmark, designed to evaluate MLLMs' capacity to interpret real-world music scores and answer complex musicological queries. Each instance in WildScore is sourced from genuine musical compositions and accompanied by authentic user-generated questions and discussions, capturing the intricacies of practical music analysis. To facilitate systematic evaluation, we propose a systematic taxonomy, comprising both high-level and fine-grained musicological ontologies. Furthermore, we frame complex music reasoning as multiple-choice question answering, enabling controlled and scalable assessment of MLLMs' symbolic music understanding. Empirical benchmarking of state-of-the-art MLLMs on WildScore reveals intriguing patterns in their visual-symbolic reasoning, uncovering both promising directions and persistent challenges for MLLMs in symbolic music reasoning and analysis. We release the dataset and code.","short_abstract":"Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, their reasoning abilities in the multimodal symbolic music domain remain largely unexplored. We introduce WildScore, the first in-the-wild multimodal symbolic music reason...","url_abs":"https://arxiv.org/abs/2509.04744","url_pdf":"https://arxiv.org/pdf/2509.04744v2","authors":"[\"Gagan Mundada\",\"Yash Vishe\",\"Amit Namburi\",\"Xin Xu\",\"Zachary Novack\",\"Julian McAuley\",\"Junda Wu\"]","published":"2025-09-05T01:54:50Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.CL\",\"eess.AS\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}