@inproceedings{tang-etal-2025-evowiki,
    title = "{E}vo{W}iki: Evaluating {LLM}s on Evolving Knowledge",
    author = "Tang, Wei  and
      Cao, Yixin  and
      Deng, Yang  and
      Ying, Jiahao  and
      Wang, Bo  and
      Yang, Yizhe  and
      Zhao, Yuyue  and
      Zhang, Qi  and
      Huang, Xuanjing  and
      Jiang, Yu-Gang  and
      Liao, Yong",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.47/",
    pages = "948--964",
    ISBN = "979-8-89176-251-0",
    abstract = "Knowledge utilization is a critical aspect of LLMs, and understanding how they adapt to evolving knowledge is essential for their effective deployment. However, existing benchmarks are predominantly static, failing to capture the evolving nature of LLMs and knowledge, leading to inaccuracies and vulnerabilities such as contamination. In this paper, we introduce EvoWiki, an evolving dataset designed to reflect knowledge evolution by categorizing information into stable, evolved, and uncharted states. EvoWiki is fully auto-updatable, enabling precise evaluation of continuously changing knowledge and newly released LLMs. Through experiments with Retrieval-Augmented Generation (RAG) and Continual Learning (CL), we evaluate how effectively LLMs adapt to evolving knowledge. Our results indicate that current models often struggle with evolved knowledge, frequently providing outdated or incorrect responses. Moreover, the dataset highlights a synergistic effect between RAG and CL, demonstrating their potential to better adapt to evolving knowledge. EvoWiki provides a robust benchmark for advancing future research on the knowledge evolution capabilities of large language models."
}