@inproceedings{zhang-etal-2026-bidirectional-lms,
    title = "Bidirectional {LM}s are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection",
    author = "Zhang, Yuwei  and
      Yu, Wenhao  and
      Feng, Shangbin  and
      Zhu, Yifan  and
      Peng, Letian  and
      Srinivasa, Jayanth  and
      Liu, Gaowen  and
      Shang, Jingbo",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.771/",
    pages = "16964--16980",
    ISBN = "979-8-89176-390-6",
    abstract = "Despite significant advances in large language models (LLMs), their knowledge memorization capabilities remain underexplored, due to the lack of standardized and high-quality testing grounds. In this paper, we introduce a novel, real-world and large-scale knowledge injection benchmark that continuously evolves without human intervention. Specifically, we propose WikiDYK, which leverages recently-added and expert-curated facts from Wikipedia{'}s ``Did You Know...'' entries. Each entry is converted into multiple question{--}answer pairs spanning diverse task formats from easy cloze prompts to complex multi-hop questions. WikiDYK currently contains 12,290 facts and 77,180 questions, and its design allows for seamless extension with future updates from Wikipedia editors. Through extensive experiments using continued pre-training, we reveal a surprising insight: despite their prevalence in modern LLMs, Causal Language Models (CLMs) demonstrate significantly weaker knowledge memorization capabilities compared to Bidirectional Language Models (BiLMs), exhibiting a 23{\%} lower accuracy in terms of reliability. To compensate for the smaller scales of current BiLMs, we introduce a modular collaborative framework utilizing ensembles of BiLMs as external knowledge repositories to integrate with LLMs. Experiment shows that this framework further improves the reliability accuracy by up to 29.1{\%}. Code: \url{https://github.com/zhang-yu-wei/WikiDYK}."
}