@inproceedings{wu-etal-2026-knowme,
    title = "{K}now{M}e-Bench: Benchmarking Person Understanding for Lifelong Digital Companions",
    author = "Wu, Tingyu  and
      Chen, Zhisheng  and
      Weng, Ziyan  and
      Wang, Shuhe  and
      Zhang, Shuo  and
      Hu, Sen  and
      Wu, Silin  and
      Lan, Qizhen  and
      Wang, Huacan  and
      Chen, Ronghao",
    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.1394/",
    pages = "30214--30238",
    ISBN = "979-8-89176-390-6",
    abstract = "Existing long-horizon memory benchmarks mostly use multi-turn dialogues or synthetic user histories, which makes retrieval performance an imperfect proxy for person understanding. We present Knowme-Bench, a publicly releasable benchmark built from long-form autobiographical narratives, where actions, context, and inner thoughts provide dense evidence for inferring stable motivations and decision principles. Knowme-Bench reconstructs each narrative into a flashback-aware, time-anchored stream and evaluates models with evidence-linked questions spanning factual recall, subjective state attribution, and principle-level reasoning. Across diverse narrative sources, retrieval-augmented systems mainly improve factual accuracy, while errors persist on temporally grounded explanations and higher-level inferences, highlighting the need for memory mechanisms beyond retrieval."
}