@inproceedings{cohen-etal-2025-small,
    title = "Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition",
    author = "Cohen, Danielle  and
      Halpern, Yoni  and
      Kahlon, Noam  and
      Oren, Joel  and
      Berkovitch, Omri  and
      Caduri, Sapir  and
      Dagan, Ido  and
      Efros, Anatoly",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.949/",
    pages = "18791--18810",
    ISBN = "979-8-89176-332-6",
    abstract = "Understanding user intents from UI interaction trajectories remains a challenging, yet crucial, frontier in intelligent agent development. While massive, datacenter-based, multi-modal large language models (MLLMs) possess greater capacity to handle the complexities of such sequences, smaller models which can run on-device to provide a privacy-preserving, low-cost, and low-latency user experience, struggle with accurate intent inference. We address these limitations by introducing a novel decomposed approach: first, we perform structured interaction summarization, capturing key information from each user action. Second, we perform intent extraction using a fine-tuned model operating on the aggregated summaries. This method improves intent understanding in resource-constrained models, even surpassing the base performance of large MLLMs."
}