@inproceedings{yaldiz-etal-2025-design,
    title = "Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative {LLM}s",
    author = "Yaldiz, Duygu Nur  and
      Bakman, Yavuz Faruk  and
      Buyukates, Baturalp  and
      Tao, Chenyang  and
      Ramakrishna, Anil  and
      Dimitriadis, Dimitrios  and
      Zhao, Jieyu  and
      Avestimehr, Salman",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.41/",
    pages = "691--713",
    ISBN = "979-8-89176-195-7",
    abstract = "Uncertainty estimation (UE) of generative large language models (LLMs) is crucial for evaluating the reliability of generated sequences. A significant subset of UE methods utilize token probabilities to assess uncertainty, aggregating multiple token probabilities into a single UE score using a scoring function. Existing scoring functions for probability-based UE, such as length-normalized scoring and semantic contribution-based weighting, are designed to solve certain aspects of the problem but exhibit limitations, including the inability to handle biased probabilities and complex semantic dependencies between tokens. To address these issues, in this work, we propose Learnable Response Scoring (LARS) function, a novel scoring function that leverages supervised data to capture complex dependencies between tokens and probabilities, thereby producing more reliable and calibrated response scores in computing the uncertainty of LLM generations. Our comprehensive experiments across question-answering and arithmetical reasoning tasks with various datasets demonstrate that LARS significantly outperforms existing scoring functions, achieving improvements of up to 16{\%} AUROC score."
}