@inproceedings{lee-etal-2026-enhancing,
    title = "Enhancing Hallucination Detection via Future Context",
    author = "Lee, Joosung  and
      Park, Cheonbok  and
      Jo, Hwiyeol  and
      Kim, Jeonghoon  and
      Park, Joonsuk  and
      Yoo, Kang Min",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.35/",
    pages = "731--749",
    ISBN = "979-8-89176-395-1",
    abstract = "Large Language Models (LLMs) are widely used to generate plausible text on online platforms, without revealing the generation process.As users increasingly encounter such black-box outputs, detecting hallucinations has become a critical challenge.To address this challenge, we focus on developing a hallucination detection framework for black-box generators.Motivated by the observation that hallucinations, once introduced, tend to persist, we sample future contexts.The sampled future contexts provide valuable clues for hallucination detection and can be effectively integrated with various sampling-based methods.We extensively demonstrate performance improvements across multiple methods using our proposed sampling approach."
}