@inproceedings{calvo-etal-2025-beyond,
    title = "Beyond instruction-conditioning, {M}o{TE}: Mixture of Task Experts for Multi-task Embedding Models",
    author = "Calvo, Miguel Romero  and
      Ding, Shuoyang  and
      Barrett, Corey D  and
      Dinu, Georgiana  and
      Karypis, George",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.findings-acl.1168/",
    pages = "22731--22746",
    ISBN = "979-8-89176-256-5",
    abstract = "Dense embeddings are fundamental to modern machine learning systems, powering Retrieval-Augmented Generation (RAG), information retrieval, and representation learning. While instruction-conditioning has become the dominant approach for embedding specialization, its direct application to low-capacity models imposes fundamental representational constraints that limit the performance gains derived from specialization. In this paper, we analyze these limitations and introduce the Mixture of Task Experts (MoTE) transformer block, which leverages task-specialized parameters trained with Task-Aware Contrastive Learning () to enhance the model{'}s ability to generate specialized embeddings. Empirical results show that MoTE achieves 64{\%} higher performance gains in retrieval datasets ($+3.27\rightarrow +5.21$) and 43{\%} higher performance gains across all datasets ($+1.81\rightarrow 2.60$). Critically, these gains are achieved without altering instructions, training data, inference time, or number of active parameters."
}