@inproceedings{li-etal-2026-beyond,
    title = "Beyond a Single Extractor: Re-thinking {HTML}-to-Text Extraction for {LLM} Pre-training",
    author = "Li, Jeffrey  and
      Gardner, Joshua P  and
      Kang, Doug  and
      Shi, Fangping  and
      Singh, Karanjeet  and
      Li, Chun-Liang  and
      Shandilya, Herumb  and
      Hall, David Leo Wright  and
      Tuzel, Oncel  and
      Liang, Percy  and
      Schmidt, Ludwig  and
      Pouransari, Hadi  and
      Faghri, Fartash",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.307/",
    pages = "5836--5861",
    ISBN = "979-8-89176-386-9"
}