{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:51:22Z","timestamp":1790610682120,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"the Noncommunicable Chronic Diseases-National Science and Technology Major Project","award":["NO. 2024ZD0532400 and NO. 2024ZD0532403"],"award-info":[{"award-number":["NO. 2024ZD0532400 and NO. 2024ZD0532403"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792700","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"2441-2452","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7001-5701","authenticated-orcid":false,"given":"Yunhao","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0117-8847","authenticated-orcid":false,"given":"Zian","family":"Jia","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9306-6106","authenticated-orcid":false,"given":"Xinyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7706-5346","authenticated-orcid":false,"given":"Kanjun","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8575-5415","authenticated-orcid":false,"given":"Yun","family":"Xiong","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Karnin","author":"Amiraz Chen","year":"2025","unstructured":"Chen Amiraz, Florin Cuconasu, Simone Filice, and Zohar S. Karnin. 2025. The Distracting Effect: Understanding Irrelevant Passages in RAG. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Sotiris Anagnostidis Dario Pavllo Luca Biggio et al. 2023. Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023 NeurIPS 2023.","DOI":"10.52202\/075280-2845"},{"key":"e_1_3_2_1_3_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR","author":"Asai Akari","year":"2024","unstructured":"Akari Asai, Zeqiu Wu, Yizhong Wang, et al., 2024. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. In The Twelfth International Conference on Learning Representations, ICLR 2024."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1160"},{"key":"e_1_3_2_1_5_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","author":"Cheng Xin","year":"2024","unstructured":"Xin Cheng, Xun Wang, Xingxing Zhang, et al., 2024. xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2404.16130"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1006"},{"key":"e_1_3_2_1_8_1","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao et al. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey. CoRR Vol. abs\/2312.10997 (2023). arXiv:2312.10997"},{"key":"e_1_3_2_1_9_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR","author":"Ge Tao","year":"2024","unstructured":"Tao Ge, Jing Hu, Lei Wang, et al., 2024. In-context Autoencoder for Context Compression in a Large Language Model. In The Twelfth International Conference on Learning Representations, ICLR 2024."},{"key":"e_1_3_2_1_10_1","unstructured":"Yang Guo Yutian Tao Yifei Ming et al. 2025. Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds. CoRR Vol. abs\/2506.03100 (2025). arXiv:2506.03100"},{"key":"e_1_3_2_1_11_1","volume-title":"REALM: Retrieval-Augmented Language Model Pre-Training. CoRR","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, et al., 2020. REALM: Retrieval-Augmented Language Model Pre-Training. CoRR, Vol. abs\/2002.08909 (2020). arXiv:2002.08909 https:\/\/arxiv.org\/abs\/2002.08909"},{"key":"e_1_3_2_1_12_1","volume-title":"Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity. In Findings of the Association for Computational Linguistics: ACL","author":"H\u00e4mmerl Katharina","year":"2023","unstructured":"Katharina H\u00e4mmerl, Alina Fastowski, Jindrich Libovick\u00fd, and Alexander Fraser. 2023. Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity. In Findings of the Association for Computational Linguistics: ACL 2023."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2404.10981"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_2_1_15_1","article-title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","volume":"24","author":"Izacard Gautier","year":"2023","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, et al., 2023. Atlas: Few-shot Learning with Retrieval Augmented Language Models. J. Mach. Learn. Res., Vol. 24 (2023), 251:1-251:43.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.08892"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1215"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.895"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_22_1","volume-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, et al., 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020."},{"key":"e_1_3_2_1_23_1","volume-title":"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases. CoRR","author":"Li Jiarui","year":"2024","unstructured":"Jiarui Li, Ye Yuan, and Zehua Zhang. 2024c. Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases. CoRR, Vol. abs\/2403.10446 (2024). arXiv:2403.10446"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.391"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Yongqi Li Xinyu Lin Wenjie Wang et al. 2024b. A Survey of Generative Search and Recommendation in the Era of Large Language Models. CoRR Vol. abs\/2404.16924 (2024). arXiv:2404.16924 doi:10.48550\/ARXIV.2404.16924","DOI":"10.48550\/ARXIV.2404.16924"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024 - Industry Track.","author":"Li Zhuowan","year":"2024","unstructured":"Zhuowan Li, Cheng Li, Mingyang Zhang, et al., 2024a. Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: EMNLP 2024 - Industry Track."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.368"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2506.10408"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_3_2_1_30_1","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR","author":"Loshchilov Ilya","year":"2025","unstructured":"Ilya Loshchilov, Cheng-Ping Hsieh, Simeng Sun, and Boris Ginsburg. 2025. nGPT: Normalized Transformer with Representation Learning on the Hypersphere. In The Thirteenth International Conference on Learning Representations, ICLR 2025."},{"key":"e_1_3_2_1_31_1","volume-title":"ACL 2025","author":"Louis Maxime","year":"2025","unstructured":"Maxime Louis, Herv\u00e9 D\u00e9jean, and St\u00e9phane Clinchant. 2025. PISCO: Pretty Simple Compression for Retrieval-Augmented Generation. In Findings of the Association for Computational Linguistics, ACL 2025. https:\/\/aclanthology.org\/2025.findings-acl.800\/"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Xinbei Ma Yeyun Gong Pengcheng He et al. 2023. Query Rewriting for Retrieval-Augmented Large Language Models. CoRR Vol. abs\/2305.14283 (2023). arXiv:2305.14283 doi:10.48550\/ARXIV.2305.14283","DOI":"10.48550\/ARXIV.2305.14283"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"e_1_3_2_1_34_1","volume-title":"ACL","author":"Pan Zhuoshi","year":"2024","unstructured":"Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, et al., 2024. LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression. In Findings of the Association for Computational Linguistics, ACL 2024."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.09252"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb00917.x"},{"key":"e_1_3_2_1_37_1","volume-title":"Efficient Transformers: A Survey. CoRR","author":"Tay Yi","year":"2020","unstructured":"Yi Tay, Mostafa Dehghani, Dara Bahri, and Donald Metzler. 2020. Efficient Transformers: A Survey. CoRR, Vol. abs\/2009.06732 (2020). arXiv:2009.06732"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.372"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","unstructured":"S. M. Towhidul Islam Tonmoy S. M. Mehedi Zaman Vinija Jain et al. 2024. A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models. CoRR Vol. abs\/2401.01313 (2024). arXiv:2401.01313 doi:10.48550\/ARXIV.2401.01313","DOI":"10.48550\/ARXIV.2401.01313"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2409.13385"},{"key":"e_1_3_2_1_41_1","volume-title":"ACL","author":"Vu Tu","year":"2024","unstructured":"Tu Vu, Mohit Iyyer, Xuezhi Wang, et al., 2024. FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation. In Findings of the Association for Computational Linguistics, ACL 2024."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"e_1_3_2_1_43_1","volume-title":"RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation. In The Twelfth International Conference on Learning Representations, ICLR","author":"Xu Fangyuan","year":"2024","unstructured":"Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2024. RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation. In The Twelfth International Conference on Learning Representations, ICLR 2024."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_2_1_45_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Yoran Ori","year":"2024","unstructured":"Ori Yoran, Tomer Wolfson, Ori Ram, and Jonathan Berant. 2024. Making Retrieval-Augmented Language Models Robust to Irrelevant Context. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","unstructured":"Hao Yu Aoran Gan Kai Zhang et al. 2024. Evaluation of Retrieval-Augmented Generation: A Survey. CoRR Vol. abs\/2405.07437 (2024). arXiv:2405.07437 doi:10.48550\/ARXIV.2405.07437","DOI":"10.48550\/ARXIV.2405.07437"},{"key":"e_1_3_2_1_47_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR","author":"Yu Wenhao","year":"2023","unstructured":"Wenhao Yu, Dan Iter, Shuohang Wang, et al., 2023. Generate rather than Retrieve: Large Language Models are Strong Context Generators. In The Eleventh International Conference on Learning Representations, ICLR 2023. OpenReview.net."},{"key":"e_1_3_2_1_48_1","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR","author":"Zhu Yun","year":"2025","unstructured":"Yun Zhu, Jia-Chen Gu, Caitlin Sikora, et al., 2025. Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection. In The Thirteenth International Conference on Learning Representations, ICLR 2025. OpenReview.net."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:33:30Z","timestamp":1775838810000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792700"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":48,"alternative-id":["10.1145\/3774904.3792700","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792700","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}