@inproceedings{suarez-etal-2026-commonlid,
    title = "{C}ommon{LID}: Re-evaluating State-of-the-Art Language Identification Performance on Web Data",
    author = "Suarez, Pedro Ortiz  and
      Burchell, Laurie  and
      Arnett, Catherine  and
      Mosquera, Rafael  and
      Monsalve, Sara Hincapi{\textbackslash}'e  and
      Vaughan, Thom  and
      Stewart, Damian  and
      Ostendorff, Malte  and
      Abdulmumin, Idris  and
      Marivate, Vukosi  and
      Muhammad, Shamsuddeen Hassan  and
      Tonja, Atnafu Lambebo  and
      Al-Khalifa, Hend  and
      Hammouda, Nadia Ghezaiel  and
      Otiende, Verrah Akinyi  and
      Wong, Tack Hwa  and
      Saydaliev, Jakhongir  and
      Nobakhtian, Melika  and
      Habibi, Muhammad Ravi Shulthan  and
      Kranti, Chalamalasetti  and
      Muchemi, Carol  and
      Nguyen, Khang  and
      Adam, Faisal Muhammad  and
      Salim, Luis Frentzen  and
      Alqifari, Reem  and
      Amol, Cynthia Jayne  and
      Imperial, Joseph Marvin  and
      Kesen, Ilker  and
      Mustafid, Ahmad  and
      Stepachev, Pavel  and
      Choshen, Leshem  and
      Anugraha, David  and
      Nayel, Hamada  and
      Yimam, Seid Muhie  and
      Putra, Vallerie Alexandra  and
      Nguyen, My Chiffon  and
      Wasi, Azmine Toushik  and
      Vadithya, Gouthami  and
      Van Der Goot, Rob  and
      C'horr, Lanwenn ar  and
      Dua, Karan  and
      Yates, Andrew  and
      Bangera, Mithil  and
      Bangera, Yeshil  and
      Patel, Hitesh Laxmichand  and
      Okabe, Shu  and
      Ilasariya, Fenal Ashokbhai  and
      Gaynullin, Dmitry  and
      Winata, Genta Indra  and
      Li, Yiyuan  and
      Mart{\{}{\textbackslash}'{\textbackslash}i{\}}nez, Juan Pablo  and
      Agarwal, Amit  and
      Hanif, Ikhlasul Akmal  and
      Ahmad, Raia Abu  and
      Adenuga, Esther  and
      Tjiaranata, Filbert Aurelian  and
      Buaphet, Weerayut  and
      Anugraha, Michael  and
      Vajjala, Sowmya  and
      Rice, Benjamin L  and
      Amirudin, Azril Hafizi  and
      Alabi, Jesujoba Oluwadara  and
      Panda, Srikant  and
      Toughrai, Yassine  and
      Kyomuhendo, Bruhan  and
      Ruffinelli, Daniel  and
      Akshata  and
      Goul{\textbackslash}{\textasciitilde}ao, Manuel  and
      Zhou, Ej  and
      Ramirez, Ingrid Gabriela Franco  and
      Aggazzotti, Cristina  and
      Dobler, Konstantin  and
      Kevin, Jun  and
      Pag{\textbackslash}`es, Quentin  and
      Andrews, Nicholas  and
      Ibrahim, Nuhu  and
      Ruckdeschel, Mattes  and
      Keleg, Amr  and
      Zhang, Mike  and
      Muziri, Casper Rufaro  and
      Samuel, Saron  and
      Takeshita, Sotaro  and
      Kerdthaisong, Kun  and
      Foppiano, Luca  and
      Dent, Rasul  and
      Green, Tommaso  and
      Wali, Ahmad Mustapha  and
      Makaaka, Kamohelo  and
      Feliren, Vicky  and
      Idris, Inshirah  and
      Celikkanat, Hande  and
      Abubakar, Abdulhamid  and
      Maillard, Jean  and
      Sagot, Beno{\{}{\textbackslash}{\textasciicircum}{\textbackslash}i{\}}t  and
      Cl{\textbackslash}'erice, Thibault  and
      Murray, Kenton  and
      Luger, Sarah K. K.",
    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.1527/",
    pages = "33063--33080",
    ISBN = "979-8-89176-390-6"
}