{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:26Z","timestamp":1784138726367,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":22,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809985","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"4397-4402","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Why Knowledge Distillation Fails to Scale in Neural Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5935-3159","authenticated-orcid":false,"given":"Shu","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Information Management, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6734-560X","authenticated-orcid":false,"given":"Rui","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Information Management, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4646-4875","authenticated-orcid":false,"given":"Junan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Management, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6846-2901","authenticated-orcid":false,"given":"Tao","family":"Fan","sequence":"additional","affiliation":[{"name":"Nanjing University of Finance and Economics, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0131-0823","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Management, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Payal Bajaj Daniel Campos Nick Craswell Li Deng Jianfeng Gao Xiaodong Liu Rangan Majumder Andrew McNamara Bhaskar Mitra Tri Nguyen et al. 2016. Ms marco: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268."},{"key":"e_1_3_2_1_2_1","volume-title":"Llm2vec: Large language models are secretly powerful text encoders. arXiv preprint arXiv:2404.05961","author":"BehnamGhader Parishad","year":"2024","unstructured":"Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. Llm2vec: Large language models are secretly powerful text encoders. arXiv preprint arXiv:2404.05961 (2024)."},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_4_1","first-page":"4794","article-title":"On the efficacy of knowledge distillation","author":"Cho Jang Hyun","year":"2019","unstructured":"Jang Hyun Cho and Bharath Hariharan. 2019. On the efficacy of knowledge distillation. In Proceedings of ICCV. 4794-4802.","journal-title":"Proceedings of ICCV."},{"key":"e_1_3_2_1_5_1","volume-title":"When MLLMs Meet ICH: A visual retrieval-augmented generation-based method for intangible cultural heritage image recognition-take Shadow Puppetry as a case. Information Processing & Management","volume":"63","author":"Fan Tao","year":"2026","unstructured":"Tao Fan, Hao Wang, Yuehua Zhao, Shu Zhou, and Bin Shi. 2026. When MLLMs Meet ICH: A visual retrieval-augmented generation-based method for intangible cultural heritage image recognition-take Shadow Puppetry as a case. Information Processing & Management, Vol. 63, 3 (2026), 104481."},{"key":"e_1_3_2_1_6_1","volume-title":"Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al.","author":"Hoffmann Jordan","year":"2022","unstructured":"Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al., 2022. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556 (2022)."},{"key":"e_1_3_2_1_7_1","first-page":"164","article-title":"Improving efficient neural ranking models with cross-architecture knowledge distillation","author":"Hofst\u00e4tter Sebastian","year":"2020","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. In Proceedings of ECIR. 164-176.","journal-title":"Proceedings of ECIR."},{"key":"e_1_3_2_1_8_1","first-page":"113","article-title":"Efficiently teaching an effective dense retriever with balanced topic aware sampling","author":"Hofst\u00e4tter Sebastian","year":"2021","unstructured":"Sebastian Hofst\u00e4tter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently teaching an effective dense retriever with balanced topic aware sampling. In Proceedings of SIGIR. 113-122.","journal-title":"Proceedings of SIGIR."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.17"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.669"},{"key":"e_1_3_2_1_13_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663.","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663."},{"key":"e_1_3_2_1_14_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730225"},{"key":"e_1_3_2_1_16_1","first-page":"16522","volume-title":"Inference Scaling Law for Retrieval Augmented Generation. In Proceedings of the AAAI Conference on Artificial Intelligence","volume":"40","author":"Zhou Shu","year":"2026","unstructured":"Shu Zhou, Yuxuan Ao, Yunyang Xuan, Xin Wang, Tao Fan, and Hao Wang. 2026 a. Inference Scaling Law for Retrieval Augmented Generation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 40. 16522-16530."},{"key":"e_1_3_2_1_17_1","first-page":"8341","volume-title":"Proceedings of the ACM Web Conference","author":"Zhou Shu","year":"2026","unstructured":"Shu Zhou, Yufei Song, Jinman Leng, Xin Wang, Tao Fan, and Hao Wang. 2026 b. Activation Caching for Retrieval-Augmented Generation. In Proceedings of the ACM Web Conference 2026. 8341-8344."},{"key":"e_1_3_2_1_18_1","first-page":"8333","volume-title":"Proceedings of the ACM Web Conference","author":"Zhou Shu","year":"2026","unstructured":"Shu Zhou, Yufei Song, Jinman Leng, Xin Wang, Tao Fan, and Hao Wang. 2026 c. Cascaded Verification Framework: A Progressive Approach for Mitigating Hallucinations in Large Language Models. In Proceedings of the ACM Web Conference 2026. 8333-8336."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2025.104200"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1231"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 8725-8738","author":"Zhou Shu","year":"2025","unstructured":"Shu Zhou, Rui Zhao, Zhengda Zhou, Haohan Yi, Xuhui Zheng, and Hao Wang. 2025c. Enhancing extractive question answering in multiparty dialogues with logical inference memory network. In Proceedings of the 31st International Conference on Computational Linguistics. 8725-8738."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-3343-5_14"}],"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":"2026-07-15T17:13:48Z","timestamp":1784135628000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":22,"alternative-id":["10.1145\/3805712.3809985","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809985","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"}}]}}