@inproceedings{xie-etal-2025-latent,
    title = "Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision",
    author = "Xie, Zhouhang  and
      Khot, Tushar  and
      Dalvi Mishra, Bhavana  and
      Surana, Harshit  and
      McAuley, Julian  and
      Clark, Peter  and
      Majumder, Bodhisattwa Prasad",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.naacl-long.554/",
    pages = "11114--11134",
    ISBN = "979-8-89176-189-6",
    abstract = "Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purpose of the discovery (i.e., goal). Still, the quality of the discovered concepts remains mixed, as it depends heavily on LLM{'}s reasoning ability and drops when the data is noisy or beyond LLM{'}s knowledge. We present Instruct-LF, a goal-oriented latent factor discovery system that integrates LLM{'}s instruction-following ability with statistical models to handle large, noisy datasets where LLM reasoning alone falls short. Instruct-LF uses LLMs to propose fine-grained, goal-related properties from documents, estimates their presence across the dataset, and applies gradient-based optimization to uncover hidden factors, where each factor is represented by a cluster of co-occurring properties. We evaluate latent factors produced by Instruct-LF on movie recommendation, text-world navigation, and legal document categorization tasks. These interpretable representations improve downstream task performance by 5-52{\%} than the best baselines and were preferred 1.8 times as often as the best alternative, on average, in human evaluation."
}