{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:37:09Z","timestamp":1785605829462,"version":"3.56.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032212993","type":"print"},{"value":"9783032213006","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-21300-6_38","type":"book-chapter","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T12:59:21Z","timestamp":1774357161000},"page":"470-480","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["XProvence: Zero-Cost Multilingual Context Pruning for\u00a0Retrieval-Augmented Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5699-7362","authenticated-orcid":false,"given":"Youssef","family":"Mohamed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9659-1551","authenticated-orcid":false,"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6363-9553","authenticated-orcid":false,"given":"Thibault","family":"Formal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8188-3391","authenticated-orcid":false,"given":"Nadezhda","family":"Chirkova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"38_CR1","unstructured":"AI@Meta: Llama 3 model card (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"38_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102938","volume":"155","author":"I Alonso","year":"2024","unstructured":"Alonso, I., Oronoz, M., Agerri, R.: Medexpqa: multilingual benchmarking of large language models for medical question answering. Artif. Intell. Med. 155, 102938 (2024)","journal-title":"Artif. Intell. Med."},{"key":"38_CR3","doi-asserted-by":"publisher","unstructured":"Artetxe, M., Ruder, S., Yogatama, D.: On the cross-lingual transferability of monolingual representations. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4623\u20134637. Association for Computational Linguistics, Online (Jul 2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.421, https:\/\/aclanthology.org\/2020.acl-main.421\/","DOI":"10.18653\/v1\/2020.acl-main.421"},{"key":"38_CR4","unstructured":"Bajaj, P., et al.: Ms marco: a human generated machine reading comprehension dataset (2018). https:\/\/arxiv.org\/abs\/1611.09268"},{"key":"38_CR5","unstructured":"Bonifacio, L., et al.: mMARCO: A multilingual version of the MS MARCO passage ranking dataset (2022). https:\/\/arxiv.org\/abs\/2108.13897"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: BGE M3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. CoRR (2024)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, X., et al.: xRAG: extreme context compression for retrieval-augmented generation with one token. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024). https:\/\/openreview.net\/forum?id=6pTlXqrO0p","DOI":"10.52202\/079017-3476"},{"key":"38_CR8","unstructured":"Chirkova, N., Formal, T., Nikoulina, V., CLINCHANT, S.: Provence: efficient and robust context pruning for retrieval-augmented generation. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"38_CR9","doi-asserted-by":"publisher","unstructured":"Chirkova, N., Rau, D., D\u00e9jean, H., Formal, T., Clinchant, S., Nikoulina, V.: Retrieval-augmented generation in multilingual settings. In: Li, S., et al., (eds.) Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024), pp. 177\u2013188. Association for Computational Linguistics, Bangkok, Thailand (Aug 2024). https:\/\/doi.org\/10.18653\/v1\/2024.knowllm-1.15, https:\/\/aclanthology.org\/2024.knowllm-1.15\/","DOI":"10.18653\/v1\/2024.knowllm-1.15"},{"key":"38_CR10","doi-asserted-by":"publisher","unstructured":"Clark, J.H., et al.: TyDi QA: A benchmark for information-seeking question answering in typologically diverse languages. Trans. Assoc. Comput. Linguist. 8, 454\u2013470 (2020). https:\/\/doi.org\/10.1162\/tacl_a_00317, https:\/\/aclanthology.org\/2020.tacl-1.30\/","DOI":"10.1162\/tacl_a_00317"},{"key":"38_CR11","doi-asserted-by":"publisher","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8440\u20138451. Association for Computational Linguistics, Online (Jul 2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.747, https:\/\/aclanthology.org\/2020.acl-main.747","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"38_CR12","doi-asserted-by":"publisher","unstructured":"Cui, M., Gao, P., Liu, W., Luan, J., Wang, B.: Multilingual machine translation with open large language models at practical scale: An empirical study. In: Chiruzzo, L., Ritter, A., Wang, L. (eds.) Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 5420\u20135443. Association for Computational Linguistics, Albuquerque, New Mexico (Apr 2025). https:\/\/doi.org\/10.18653\/v1\/2025.naacl-long.280, https:\/\/aclanthology.org\/2025.naacl-long.280\/","DOI":"10.18653\/v1\/2025.naacl-long.280"},{"key":"38_CR13","unstructured":"Dang, J., et al.: Aya expanse: Combining research breakthroughs for a new multilingual frontier (2024). https:\/\/arxiv.org\/abs\/2412.04261"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Hwang, T., Jeong, S., Cho, S., Han, S., Park, J.C.: DSLR: document refinement with sentence-level re-ranking and reconstruction to enhance retrieval-augmented generation. In: Proceedings of the 3rd Workshop on Knowledge Augmented Methods for NLP, pp. 73\u201392 (2024)","DOI":"10.18653\/v1\/2024.knowledgenlp-1.6"},{"key":"38_CR15","doi-asserted-by":"publisher","unstructured":"Jiang, H., Wu, Q., Lin, C.Y., Yang, Y., Qiu, L.: LLMLingua: Compressing prompts for accelerated inference of large language models. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 13358\u201313376. Association for Computational Linguistics, Singapore (Dec 2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.825, https:\/\/aclanthology.org\/2023.emnlp-main.825\/","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"38_CR16","unstructured":"K, K., Wang, Z., Mayhew, S., Roth, D.: Cross-lingual ability of multilingual bert: an empirical study. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=HJeT3yrtDr"},{"key":"38_CR17","unstructured":"Lewis, P., et\u00a0al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural Inform. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"38_CR18","doi-asserted-by":"publisher","unstructured":"Longpre, S., Lu, Y., Daiber, J.: MKQA: a linguistically diverse benchmark for multilingual open domain question answering. Trans. Assoc. Comput. Linguist. 9, 1389\u20131406 (2021). https:\/\/doi.org\/10.1162\/tacl_a_00433, https:\/\/aclanthology.org\/2021.tacl-1.82\/","DOI":"10.1162\/tacl_a_00433"},{"key":"38_CR19","doi-asserted-by":"publisher","unstructured":"Louis, M., D\u00e9jean, H., Clinchant, S.: PISCO: pretty simple compression for retrieval-augmented generation. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 15506\u201315521. Association for Computational Linguistics, Vienna, Austria (Jul 2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.800, https:\/\/aclanthology.org\/2025.findings-acl.800\/","DOI":"10.18653\/v1\/2025.findings-acl.800"},{"key":"38_CR20","unstructured":"Nogueira, R., Cho, K.: Passage re-ranking with bert (2020). https:\/\/arxiv.org\/abs\/1901.04085"},{"key":"38_CR21","doi-asserted-by":"publisher","unstructured":"Pires, T., Schlinger, E., Garrette, D.: How multilingual is multilingual BERT? In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4996\u20135001. Association for Computational Linguistics, Florence, Italy (Jul 2019). https:\/\/doi.org\/10.18653\/v1\/P19-1493, https:\/\/aclanthology.org\/P19-1493\/","DOI":"10.18653\/v1\/P19-1493"},{"key":"38_CR22","doi-asserted-by":"publisher","unstructured":"Qin, Z., et al.: Large language models are effective text rankers with pairwise ranking prompting. In: Duh, K., Gomez, H., Bethard, S. (eds.) Findings of the Association for Computational Linguistics: NAACL 2024, pp. 1504\u20131518. Association for Computational Linguistics, Mexico City, Mexico (Jun 2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-naacl.97, https:\/\/aclanthology.org\/2024.findings-naacl.97\/","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"38_CR23","doi-asserted-by":"publisher","unstructured":"Rau, D., et al.: BERGEN: A benchmarking library for retrieval-augmented generation. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 7640\u20137663. Association for Computational Linguistics, Miami, Florida, USA (Nov 2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.449, https:\/\/aclanthology.org\/2024.findings-emnlp.449\/","DOI":"10.18653\/v1\/2024.findings-emnlp.449"},{"key":"38_CR24","doi-asserted-by":"publisher","unstructured":"Rau, D., Wang, S., D\u00e9jean, H., Clinchant, S., Kamps, J.: Context embeddings for efficient answer generation in retrieval-augmented generation. In: Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, pp. 493\u2013502. WSDM \u201925, Association for Computing Machinery, New York, NY, USA (2025). https:\/\/doi.org\/10.1145\/3701551.3703527, https:\/\/doi.org\/10.1145\/3701551.3703527","DOI":"10.1145\/3701551.3703527"},{"key":"38_CR25","doi-asserted-by":"publisher","unstructured":"Shen, X., Asai, A., Byrne, B., De Gispert, A.: xPQA: cross-lingual product question answering in 12 languages. In: Sitaram, S., Beigman Klebanov, B., Williams, J.D. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pp. 103\u2013115. Association for Computational Linguistics, Toronto, Canada (Jul 2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-industry.12, https:\/\/aclanthology.org\/2023.acl-industry.12\/","DOI":"10.18653\/v1\/2023.acl-industry.12"},{"key":"38_CR26","doi-asserted-by":"publisher","unstructured":"Sun, W., et al.: Is ChatGPT good at search? investigating large language models as re-ranking agents. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14918\u201314937. Association for Computational Linguistics, Singapore (Dec 2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.923, https:\/\/aclanthology.org\/2023.emnlp-main.923\/","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"38_CR27","unstructured":"Wang, Z., Araki, J., Jiang, Z., Parvez, M.R., Neubig, G.: Learning to filter context for retrieval-augmented generation (2023). https:\/\/arxiv.org\/abs\/2311.08377"},{"key":"38_CR28","doi-asserted-by":"publisher","unstructured":"Wu, S., Dredze, M.: Beto, bentz, becas: The surprising cross-lingual effectiveness of BERT. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 833\u2013844. Association for Computational Linguistics, Hong Kong, China (Nov 2019). https:\/\/doi.org\/10.18653\/v1\/D19-1077, https:\/\/aclanthology.org\/D19-1077\/","DOI":"10.18653\/v1\/D19-1077"},{"key":"38_CR29","unstructured":"Xu, F., Shi, W., Choi, E.: Recomp: Improving retrieval-augmented lms with compression and selective augmentation. arXiv preprint arXiv:2310.04408 (2023)"},{"key":"38_CR30","doi-asserted-by":"publisher","unstructured":"Yoon, C., Lee, T., Hwang, H., Jeong, M., Kang, J.: CompAct: compressing retrieved documents actively for question answering. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 21424\u201321439. Association for Computational Linguistics, Miami, Florida, USA (Nov 2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.1194, https:\/\/aclanthology.org\/2024.emnlp-main.1194\/","DOI":"10.18653\/v1\/2024.emnlp-main.1194"},{"key":"38_CR31","doi-asserted-by":"publisher","unstructured":"Zhang, X., et al.: MIRACL: a multilingual retrieval dataset covering 18 diverse languages. Trans. Assoc. Comput. Linguist. 11, 1114\u20131131 (2023). https:\/\/doi.org\/10.1162\/tacl_a_00595, https:\/\/aclanthology.org\/2023.tacl-1.63\/","DOI":"10.1162\/tacl_a_00595"},{"key":"38_CR32","doi-asserted-by":"publisher","unstructured":"Zhuang, H., et al.: Beyond yes and no: improving zero-shot LLM rankers via scoring fine-grained relevance labels. In: Duh, K., Gomez, H., Bethard, S. (eds.) Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pp. 358\u2013370. Association for Computational Linguistics, Mexico City, Mexico (Jun 2024). https:\/\/doi.org\/10.18653\/v1\/2024.naacl-short.31, https:\/\/aclanthology.org\/2024.naacl-short.31\/","DOI":"10.18653\/v1\/2024.naacl-short.31"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21300-6_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T12:59:30Z","timestamp":1774357170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21300-6_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032212993","9783032213006"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21300-6_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}