WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval.

@inproceedings{azzopardi-2026-webfaq, author = {Leif Azzopardi and Michael Dinzinger and Alistair Moffat and Laura Caspari and Ali Salman and Paul Thomas and Guido Zuccon and Irvin Topi and Jelena Mitrovic and Michael Granitzer}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {3138--3144}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3808621}, doi = {https://doi.org/10.1145/3805712.3808621} }