{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T07:41:34Z","timestamp":1774510894315,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T00:00:00Z","timestamp":1741564800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Netherlands Organization for Scientific Research","award":["ISC.CC.016"],"award-info":[{"award-number":["ISC.CC.016"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,10]]},"DOI":"10.1145\/3701551.3703527","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T12:30:16Z","timestamp":1740573016000},"page":"493-502","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Context Embeddings for Efficient Answer Generation in Retrieval-Augmented Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1964-1356","authenticated-orcid":false,"given":"David","family":"Rau","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0726-5250","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9837-5358","authenticated-orcid":false,"given":"Herv\u00e9","family":"D\u00e9jean","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Grenoble, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2367-8837","authenticated-orcid":false,"given":"St\u00e9phane","family":"Clinchant","sequence":"additional","affiliation":[{"name":"Naver Labs Europe, Grenoble, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6614-0087","authenticated-orcid":false,"given":"Jaap","family":"Kamps","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2025,3,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Luke Zettlemoyer, Hannaneh Hajishirzi, and Wen-tau Yih.","author":"Asai Akari","year":"2024","unstructured":"Akari Asai, Zexuan Zhong, Danqi Chen, Pang Wei Koh, Luke Zettlemoyer, Hannaneh Hajishirzi, and Wen-tau Yih. 2024. Reliable, Adaptable, and Attributable Language Models with Retrieval. arXiv preprint arXiv:2403.03187 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00338"},{"key":"e_1_3_2_1_3_1","volume-title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. arXiv preprint arXiv:2405.13792","author":"Cheng Xin","year":"2024","unstructured":"Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, and Dongyan Zhao. 2024. xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. arXiv preprint arXiv:2405.13792 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Alexis Chevalier AlexanderWettig Anirudh Ajith and Danqi Chen. 2023. Adapting Language Models to Compress Contexts. arXiv:2305.14788 [cs.CL]","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Florin Cuconasu Giovanni Trappolini Federico Siciliano Simone Filice Cesare Campagnano Yoelle Maarek Nicola Tonellotto and Fabrizio Silvestri. 2024. The Power of Noise: Redefining Retrieval for RAG Systems. arXiv:2401.14887 [cs.IR]","DOI":"10.1145\/3626772.3657834"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3291012"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1346"},{"key":"e_1_3_2_1_8_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=uREj4ZuGJE","author":"Ge Tao","year":"2024","unstructured":"Tao Ge, Hu Jing, Lei Wang, Xun Wang, Si-Qing Chen, and Furu Wei. 2024. In-context Autoencoder for Context Compression in a Large Language Model. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=uREj4ZuGJE"},{"key":"e_1_3_2_1_9_1","volume-title":"Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543","author":"He Pengcheng","year":"2021","unstructured":"Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543 (2021)."},{"key":"e_1_3_2_1_10_1","volume-title":"RAGGED: Towards Informed Design of Retrieval Augmented Generation Systems. arXiv:2403.09040 [cs.CL]","author":"Hsia Jennifer","year":"2024","unstructured":"Jennifer Hsia, Afreen Shaikh, Zhiruo Wang, and Graham Neubig. 2024. RAGGED: Towards Informed Design of Retrieval Augmented Generation Systems. arXiv:2403.09040 [cs.CL]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Gautier Izacard and Edouard Grave. 2021. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. http:\/\/arxiv.org\/abs\/2007.01282 arXiv:2007.01282 [cs].","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_2_1_12_1","volume-title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. Atlas: Few-shot Learning with Retrieval Augmented Language Models. http:\/\/arxiv.org\/abs\/2208.03299 arXiv:2208.03299 [cs]."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1028"},{"key":"e_1_3_2_1_15_1","unstructured":"Matt Gardner Johannes Welbl Nelson F. Liu. 2017. Crowdsourcing Multiple Choice Science Questions. arXiv:1707.06209v1."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_18_1","volume-title":"SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789","author":"Lassance Carlos","year":"2024","unstructured":"Carlos Lassance, Herv\u00e9 D\u00e9jean, Thibault Formal, and St\u00e9phane Clinchant. 2024. SPLADE-v3: New baselines for SPLADE. arXiv preprint arXiv:2403.06789 (2024)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_1_20_1","unstructured":"Yucheng Li. 2023. Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering. arXiv:2304.12102 [cs.CL]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Nelson F. Liu Kevin Lin John Hewitt Ashwin Paranjape Michele Bevilacqua Fabio Petroni and Percy Liang. 2023. Lost in the Middle: How Language Models Use Long Contexts. https:\/\/doi.org\/10.48550\/arXiv.2307.03172 arXiv:2307.03172 [cs].","DOI":"10.48550\/arXiv.2307.03172"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.765"},{"key":"e_1_3_2_1_24_1","unstructured":"Niklas Muennighoff Hongjin Su LiangWang Nan Yang FuruWei Tao Yu Amanpreet Singh and Douwe Kiela. 2024. Generative Representational Instruction Tuning. arXiv:2402.09906 [cs.CL]"},{"key":"e_1_3_2_1_25_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. Ms marco: A human-generated machine reading comprehension dataset. (2016)."},{"key":"e_1_3_2_1_26_1","volume-title":"Anton Lozhkov, Margaret Mitchell, Colin Raffel, Leandro Von Werra, and Thomas Wolf.","author":"Penedo Guilherme","year":"2024","unstructured":"Guilherme Penedo, Hynek Kydl\u00ed?ek, Loubna Ben allal, Anton Lozhkov, Margaret Mitchell, Colin Raffel, Leandro Von Werra, and Thomas Wolf. 2024. The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale. arXiv:2406.17557 [cs.CL] https:\/\/arxiv.org\/abs\/2406.17557"},{"key":"e_1_3_2_1_27_1","volume-title":"James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, et al.","author":"Petroni Fabio","year":"2020","unstructured":"Fabio Petroni, Aleksandra Piktus, Angela Fan, Patrick Lewis, Majid Yazdani, Nicola De Cao, James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, et al. 2020. KILT: a benchmark for knowledge intensive language tasks. arXiv preprint arXiv:2009.02252 (2020)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_29_1","volume-title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. arXiv:2407.01102 [cs.CL] https:\/\/arxiv.org\/abs\/2407.01102","author":"Rau David","year":"2024","unstructured":"David Rau, Herv\u00e9 D\u00e9jean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Vassilina Nikoulina, and St\u00e9phane Clinchant. 2024. BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. arXiv:2407.01102 [cs.CL] https:\/\/arxiv.org\/abs\/2407.01102"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.566"},{"key":"e_1_3_2_1_31_1","volume-title":"LLoCO: Learning Long Contexts Offline. arXiv preprint arXiv:2404.07979","author":"Tan Sijun","year":"2024","unstructured":"Sijun Tan, Xiuyu Li, Shishir Patil, Ziyang Wu, Tianjun Zhang, Kurt Keutzer, Joseph E Gonzalez, and Raluca Ada Popa. 2024. LLoCO: Learning Long Contexts Offline. arXiv preprint arXiv:2404.07979 (2024)."},{"key":"e_1_3_2_1_32_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288 [cs.CL]"},{"key":"e_1_3_2_1_33_1","volume-title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation. arXiv:2310.04408 [cs.CL]","author":"Xu Fangyuan","year":"2023","unstructured":"Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2023. RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation. arXiv:2310.04408 [cs.CL]"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1237"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18--1259"},{"key":"e_1_3_2_1_36_1","unstructured":"Yun Zhu Jia-Chen Gu Caitlin Sikora Ho Ko Yinxiao Liu Chu-Cheng Lin Lei Shu Liangchen Luo Lei Meng Bang Liu et al. 2024. Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection. arXiv preprint arXiv:2405.16178 (2024)."}],"event":{"name":"WSDM '25: The Eighteenth ACM International Conference on Web Search and Data Mining","location":"Hannover Germany","acronym":"WSDM '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703527","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701551.3703527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T09:07:27Z","timestamp":1755767247000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701551.3703527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,10]]},"references-count":36,"alternative-id":["10.1145\/3701551.3703527","10.1145\/3701551"],"URL":"https:\/\/doi.org\/10.1145\/3701551.3703527","relation":{},"subject":[],"published":{"date-parts":[[2025,3,10]]},"assertion":[{"value":"2025-03-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}