{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:04:22Z","timestamp":1784138662531,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"OpenWebSearch.EU","award":["101070014"],"award-info":[{"award-number":["101070014"]}]},{"name":"DEKIS","award":["05119210"],"award-info":[{"award-number":["05119210"]}]},{"name":"B2B-Konnekt","award":["28DI110A23"],"award-info":[{"award-number":["28DI110A23"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808621","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3138-3144","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["WebFAQ 2.0: A Multilingual QA Dataset with Mined Hard Negatives for Dense Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1747-5643","authenticated-orcid":false,"given":"Michael","family":"Dinzinger","sequence":"first","affiliation":[{"name":"University of Passau, Passau, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6670-3211","authenticated-orcid":false,"given":"Laura","family":"Caspari","sequence":"additional","affiliation":[{"name":"University of Passau, Passau, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2422-6707","authenticated-orcid":false,"given":"Ali","family":"Salman","sequence":"additional","affiliation":[{"name":"University of Passau, Passau, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8298-5039","authenticated-orcid":false,"given":"Irvin","family":"Topi","sequence":"additional","affiliation":[{"name":"University of Passau, Passau, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3220-8749","authenticated-orcid":false,"given":"Jelena","family":"Mitrovi\u0107","sequence":"additional","affiliation":[{"name":"University of Passau, Passau, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3566-5507","authenticated-orcid":false,"given":"Michael","family":"Granitzer","sequence":"additional","affiliation":[{"name":"University of Passau, Passau, Germany and Interdisciplinary Transformation University, Linz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.421"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531926"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2108.13897"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Yinqiong Cai Jiafeng Guo Yixing Fan Qingyao Ai Ruqing Zhang and Xueqi Cheng. 2022. Hard Negatives or False Negatives: Correcting Pooling Bias in Training Neural Ranking Models. doi:10.48550\/ARXIV.2209.05072","DOI":"10.48550\/ARXIV.2209.05072"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00317"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3731934"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Michael Dinzinger Saber Zerhoudi Jelena Mitrovi? and Michael Granitzer. 2024. OWLer: A Distributed and Collaborative Open Web Crawler. (2024). doi:10.5281\/ZENODO.13863478","DOI":"10.5281\/ZENODO.13863478"},{"key":"e_1_3_2_1_9_1","volume-title":"MMTEB: Massive Multilingual Text Embedding Benchmark. In The 13th International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zl3pfz4VCV","author":"Kenneth","unstructured":"Kenneth Enevoldsen et al. 2025. MMTEB: Massive Multilingual Text Embedding Benchmark. In The 13th International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zl3pfz4VCV"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Gemma Team. 2024. Gemma 2: Improving Open Language Models at a Practical Size. doi:10.48550\/ARXIV.2408.00118","DOI":"10.48550\/ARXIV.2408.00118"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Matthew Henderson Rami Al-Rfou Brian Strope Yun-hsuan Sung Laszlo Lukacs Ruiqi Guo Sanjiv Kumar Balint Miklos and Ray Kurzweil. 2017. Efficient Natural Language Response Suggestion for Smart Reply. doi:10.48550\/ARXIV.1705.00652","DOI":"10.48550\/ARXIV.1705.00652"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56069-9_10"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Sebastian Hofst\u00e4tter Sophia Althammer Michael Schr\u00f6der Mete Sertkan and Allan Hanbury. 2020. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. doi:10.48550\/ARXIV.2010.02666","DOI":"10.48550\/ARXIV.2010.02666"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.184"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"e_1_3_2_1_17_1","first-page":"193","volume-title":"Proceedings of the 24th Annual Conference of the European Association for Machine Translation. European Association for Machine Translation","author":"Kocmi Tom","year":"2023","unstructured":"Tom Kocmi and Christian Federmann. 2023. Large Language Models Are State-of-the-Art Evaluators of Translation Quality. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation. European Association for Machine Translation, Tampere, Finland, 193-203. https:\/\/aclanthology.org\/2023.eamt-1.19\/"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.653"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00415"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00433"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Meta Team. 2024. The Llama 3 Herd of Models. doi:10.48550\/ARXIV.2407.21783","DOI":"10.48550\/ARXIV.2407.21783"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Gabriel de Souza P. Moreira Radek Osmulski Mengyao Xu Ronay Ak Benedikt Schifferer and Even Oldridge. 2024. NV-Retriever: Improving text embedding models with effective hard-negative mining. doi:10.48550\/ARXIV.2407.15831","DOI":"10.48550\/ARXIV.2407.15831"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"e_1_3_2_1_24_1","first-page":"591","volume-title":"Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation. Association for Computational Linguistics","author":"Nguyen Thanh-Do","year":"2023","unstructured":"Thanh-Do Nguyen, Chi Minh Bui, Thi-Hai-Yen Vuong, and Xuan-Hieu Phan. 2023. Passage-based BM25 Hard Negatives: A Simple and Effective Negative Sampling Strategy For Dense Retrieval. In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation. Association for Computational Linguistics, Hong Kong, China, 591-599. https:\/\/aclanthology.org\/2023.paclic-1.59\/"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Qwen Team. 2024. Qwen2.5 Technical Report. doi:10.48550\/ARXIV.2412.15115","DOI":"10.48550\/ARXIV.2412.15115"},{"key":"e_1_3_2_1_27_1","volume-title":"Michael G\u00fcnther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Andreas Koukounas, Nan Wang, and Han Xiao.","author":"Sturua Saba","year":"2024","unstructured":"Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael G\u00fcnther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Andreas Koukounas, Nan Wang, and Han Xiao. 2024. jina-embeddings-v3: Multilingual Embeddings With Task LoRA. arXiv:2409.10173 [cs.CL] https:\/\/arxiv.org\/abs\/2409.10173"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.481"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-07959-6_17"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrl-1.12"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_0059510.1162\/tacl_a_00595"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:11:41Z","timestamp":1784135501000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808621"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":31,"alternative-id":["10.1145\/3805712.3808621","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808621","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}