@inproceedings{pang-naylor-etal-2025-controllable,
    title = "Controllable Clustering with {LLM}-driven Embeddings",
    author = "Pang-Naylor, Kerria  and
      Manivasagan, Shivani  and
      Zhong, Aitong  and
      Garg, Mehak  and
      Mondello, Nicholas  and
      Buckner, Blake  and
      Chang, Jonathan P.  and
      Mahajan, Khyati  and
      Hashemi, Masoud  and
      Casati, Fabio",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.48/",
    pages = "686--702",
    ISBN = "979-8-89176-333-3",
    abstract = "Given the inherent subjectivity of similarity in text, fully unsupervised text clustering is unlikely to produce groupings that work across a variety of use cases. Traditional techniques to guide clustering rely on costly, time-consuming human feedback and/or pre-existing labels. Leveraging recent advancements in LLMs and decoder-only embedding models, we present techniques to effectively control text embeddings with minimal human input: prefix instructions and LLM preprocessing. We evaluate clustering performance for datasets with multiple independent ground-truth labels, or perspectives, and find that these techniques can be used to improve clustering for one perspective or use case, at the cost of a tradeoff in performance for another use case."
}