@inproceedings{gupta-etal-2025-polysemantic,
    title = "Polysemantic Dropout: Conformal {OOD} Detection for Specialized {LLM}s",
    author = "Gupta, Ayush  and
      Kaur, Ramneet  and
      Roy, Anirban  and
      Cobb, Adam D.  and
      Chellappa, Rama  and
      Jha, Susmit",
    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/author-page-yu-wang-polytechnic/2025.emnlp-main.595/",
    doi = "10.18653/v1/2025.emnlp-main.595",
    pages = "11768--11781",
    ISBN = "979-8-89176-332-6",
    abstract = "We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs). Despite achieving state-of-the-art performance on in-domain tasks through fine-tuning, specialized LLMs remain vulnerable to incorrect or unreliable outputs when presented with OOD inputs, posing risks in critical applications. Our method leverages the Inductive Conformal Anomaly Detection (ICAD) framework, using a new non-conformity measure based on the model{'}s dropout tolerance. Motivated by recent findings on polysemanticity and redundancy in LLMs, we hypothesize that in-domain inputs exhibit higher dropout tolerance than OOD inputs. We aggregate dropout tolerance across multiple layers via a valid ensemble approach, improving detection while maintaining theoretical false alarm bounds from ICAD. Experiments with medical-specialized LLMs show that our approach detects OOD inputs better than baseline methods, with AUROC improvements of 2{\%} to 37{\%} when treating OOD datapoints as positives and in-domain test datapoints as negatives."
}