The k-nearest-neighbor language model (kNN-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 kNN-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 kNN-LM on low-frequency tokens, examining prediction probability, retrieval accuracy, token distribution in the datastore, and approximation error of the product quantization. Our experimental results reveal that kNN-LM does not improve prediction performance for low-frequency tokens but mainly benefits high-frequency tokens regardless of long-tail contexts in the datastore.
@article{arxiv.2503.22426,
title = {Long-Tail Crisis in Nearest Neighbor Language Models},
author = {Yuto Nishida and Makoto Morishita and Hiroyuki Deguchi and Hidetaka Kamigaito and Taro Watanabe},
journal= {arXiv preprint arXiv:2503.22426},
year = {2025}
}