@inproceedings{nishida-etal-2025-long,
    title = "Long-Tail Crisis in Nearest Neighbor Language Models",
    author = "Nishida, Yuto  and
      Morishita, Makoto  and
      Deguchi, Hiroyuki  and
      Kamigaito, Hidetaka  and
      Watanabe, Taro",
    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/Ingest-2025-COMPUTEL/2025.findings-naacl.331/",
    pages = "5965--5978",
    ISBN = "979-8-89176-195-7",
    abstract = "The $k$-nearest-neighbor language model ($k$NN-LM), one of the retrieval-augmented language models, improves the perplexity for given text by directly accessing a large datastore built from any text data during inference.A widely held hypothesis for the success of $k$NN-LM is that its explicit memory, i.e., the datastore, enhances predictions for long-tail phenomena.However, prior works have primarily shown its ability to retrieve long-tail contexts, leaving the model`s performance remain underexplored in estimating the probabilities of long-tail target tokens during inference.In this paper, we investigate the behavior of $k$NN-LM on low-frequency tokens, examining prediction probability, retrieval accuracy, and token distribution in the datastore.Our experimental results reveal that $k$NN-LM does not improve prediction performance for low-frequency tokens but mainly benefits high-frequency tokens regardless of long-tail contexts in the datastore."
}