{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:48:25Z","timestamp":1774399705859,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"name":"Research Grants Council of Hong Kong","award":["PolyU\/15209724, PolyU\/15207821, PolyU\/15207122, PolyU\/15213323"],"award-info":[{"award-number":["PolyU\/15209724, PolyU\/15207821, PolyU\/15207122, PolyU\/15213323"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3729973","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T14:55:26Z","timestamp":1752504926000},"page":"1339-1349","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Training and Inference Scaling Laws in Generative Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9857-6639","authenticated-orcid":false,"given":"Hongru","family":"Cai","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6932-4228","authenticated-orcid":false,"given":"Yongqi","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5621-9648","authenticated-orcid":false,"given":"Ruifeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5199-1428","authenticated-orcid":false,"given":"Wenjie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6336-7684","authenticated-orcid":false,"given":"Zhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7360-8864","authenticated-orcid":false,"given":"Wenjie","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocab":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocab":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Newsha Ardalani Carole-Jean Wu Zeliang Chen Bhargav Bhushanam and Adnan Aziz. 2022. Understanding Scaling Laws for Recommendation Models. arxiv:2208.08489"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems (NIPS '22)","author":"Bevilacqua Michele","year":"2022","unstructured":"Michele Bevilacqua, Giuseppe Ottaviano, Patrick Lewis, Wen-tau Yih, Sebastian Riedel, and Fabio Petroni. 2022. Autoregressive search engines: generating substrings as document identifiers. In Proceedings of the 36th International Conference on Neural Information Processing Systems (NIPS '22)."},{"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 et al. 2020. Language Models are Few-Shot Learners."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591631"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531827"},{"key":"e_1_3_2_1_6_1","volume-title":"Autoregressive Entity Retrieval. In 9th International Conference on Learning Representations, ICLR 2021","author":"Cao Nicola De","year":"2021","unstructured":"Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2021. Autoregressive Entity Retrieval. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research).","author":"Dehghani Mostafa","year":"2023","unstructured":"Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Peter Steiner, et al., 2023. Scaling Vision Transformers to 22 Billion Parameters. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)."},{"key":"e_1_3_2_1_9_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Du Zhengxiao","year":"2024","unstructured":"Zhengxiao Du, Aohan Zeng, Yuxiao Dong, and Jie Tang. 2024. Understanding Emergent Abilities of Language Models from the Loss Perspective. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657743"},{"key":"e_1_3_2_1_11_1","volume-title":"Yang Yang, and Yanqi Zhou.","author":"Hestness Joel","year":"2017","unstructured":"Joel Hestness, Sharan Narang, Newsha Ardalani, Gregory Diamos, Heewoo Jun, Hassan Kianinejad, Md. Mostofa Ali Patwary, Yang Yang, and Yanqi Zhou. 2017. Deep Learning Scaling is Predictable, Empirically. arxiv:1712.00409"},{"key":"e_1_3_2_1_12_1","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de Las Casas Lisa Anne Hendricks Johannes Welbl Aidan Clark Thomas Hennigan Eric Noland Katherine Millican George van den Driessche Bogdan Damoc Aurelia Guy Simon Osindero Kar\u00e9n Simonyan Erich Elsen Oriol Vinyals Jack Rae and Laurent Sifre. 2022. An empirical analysis of compute-optimal large language model training. In Advances in Neural Information Processing Systems Vol. 35."},{"key":"e_1_3_2_1_13_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research). 4904-4916","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research). 4904-4916."},{"key":"e_1_3_2_1_15_1","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. arxiv:2001.08361"},{"key":"e_1_3_2_1_16_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 18661-18673."},{"key":"e_1_3_2_1_17_1","volume-title":"Natural Questions: A Benchmark for Question Answering Research. Transactions of the Association for Computational Linguistics","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, et al., 2019. Natural Questions: A Benchmark for Question Answering Research. Transactions of the Association for Computational Linguistics (2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.92"},{"key":"e_1_3_2_1_20_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. arxiv:1910.13461","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. arxiv:1910.13461"},{"key":"e_1_3_2_1_21_1","unstructured":"Yongqi Li Xinyu Lin Wenjie Wang Fuli Feng Liang Pang Wenjie Li Liqiang Nie Xiangnan He and Tat-Seng Chua. 2024a. A Survey of Generative Search and Recommendation in the Era of Large Language Models. arxiv:2404.16924 [cs.IR] https:\/\/arxiv.org\/abs\/2404.16924"},{"key":"e_1_3_2_1_22_1","volume-title":"Generative retrieval for conversational question answering. Information Processing and Management","author":"Li Yongqi","year":"2023","unstructured":"Yongqi Li, Nan Yang, Liang Wang, Furu Wei, and Wenjie Li. 2023a. Generative retrieval for conversational question answering. Information Processing and Management (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.366"},{"key":"e_1_3_2_1_24_1","unstructured":"Yongqi Li Nan Yang Liang Wang Furu Wei and Wenjie Li. 2024b. Learning to rank in generative retrieval (AAAI'24\/IAAI'24\/EAAI'24)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657807"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.510"},{"key":"e_1_3_2_1_27_1","volume-title":"MS MARCO: A Human-Generated MAchine Reading COmprehension Dataset. https:\/\/openreview.net\/forum?id=Hk1iOLcle","author":"Nguyen Tri","year":"2017","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2017. MS MARCO: A Human-Generated MAchine Reading COmprehension Dataset. https:\/\/openreview.net\/forum?id=Hk1iOLcle"},{"key":"e_1_3_2_1_28_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida et al. 2024. GPT-4 Technical Report. arxiv:2303.08774"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.83"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research). 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research). 8748-8763."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619590"},{"key":"e_1_3_2_1_32_1","volume-title":"Liu","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research (2020)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.336"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Stephen Robertson and Hugo Zaragoza. 2009. The Probabilistic Relevance Framework: BM25 and Beyond. Found. Trends Inf. Retr. (2009).","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"G. Salton A. Wong and C. S. Yang. 1975. A vector space model for automatic indexing. Commun. ACM (1975).","DOI":"10.1145\/361219.361220"},{"key":"e_1_3_2_1_36_1","unstructured":"Weiwei Sun Lingyong Yan Zheng Chen Shuaiqiang Wang Haichao Zhu Pengjie Ren Zhumin Chen Dawei Yin Maarten Rijke and Zhaochun Ren. 2023. Learning to Tokenize for Generative Retrieval. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Yubao Tang Ruqing Zhang Jiafeng Guo Maarten de Rijke Wei Chen and Xueqi Cheng. 2024. Listwise Generative Retrieval Models via a Sequential Learning Process. ACM Trans. Inf. Syst. (2024).","DOI":"10.1145\/3653712"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3601857"},{"key":"e_1_3_2_1_39_1","first-page":"09288","volume":"2307","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, et al., 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv:2307.09288","journal-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295378"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602126"},{"key":"e_1_3_2_1_42_1","unstructured":"Yunli Wang Zixuan Yang Zhen Zhang Zhiqiang Wang Jian Yang Shiyang Wen Peng Jiang and Kun Gai. 2024. Scaling Laws for Online Advertisement Retrieval. arxiv:2411.13322"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614993"},{"key":"e_1_3_2_1_44_1","volume-title":"Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022. Emergent Abilities of Large Language Models. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_2_1_45_1","unstructured":"Yangzhen Wu Zhiqing Sun Shanda Li Sean Welleck and Yiming Yang. 2024. Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models. arxiv:2408.00724"},{"key":"e_1_3_2_1_46_1","volume-title":"Auto Search Indexer for End-to-End Document Retrieval. In Findings of the Association for Computational Linguistics: EMNLP","author":"Yang Tianchi","year":"2023","unstructured":"Tianchi Yang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, and Qi Zhang. 2023. Auto Search Indexer for End-to-End Document Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645477"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657746"},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML'24)","author":"Zhai Jiaqi","year":"2025","unstructured":"Jiaqi Zhai, Lucy Liao, Xing Liu, Yueming Wang, Rui Li, Xuan Cao, Leon Gao, Zhaojie Gong, Fangda Gu, Jiayuan He, Yinghai Lu, and Yu Shi. 2025. Actions speak louder than words: trillion-parameter sequential transducers for generative recommendations. In Proceedings of the 41st International Conference on Machine Learning (ICML'24)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research).","author":"Zhang Buyun","year":"2024","unstructured":"Buyun Zhang, Liang Luo, Yuxin Chen, Jade Nie, Xi Liu, Shen Li, Yanli Zhao, Yuchen Hao, Yantao Yao, Ellie Dingqiao Wen, Jongsoo Park, Maxim Naumov, and Wenlin Chen. 2024b. Wukong: Towards a Scaling Law for Large-Scale Recommendation. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688129"},{"key":"e_1_3_2_1_53_1","volume-title":"In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS '23)","author":"Zhang Hailin","year":"2024","unstructured":"Hailin Zhang, Yujing Wang, Qi Chen, Ruiheng Chang, Ting Zhang, Ziming Miao, Yingyan Hou, Yang Ding, Xupeng Miao, et al., 2024c. In Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS '23)."},{"key":"e_1_3_2_1_54_1","unstructured":"Shengyao Zhuang Houxing Ren Linjun Shou Jian Pei Ming Gong Guido Zuccon and Daxin Jiang. 2023a. Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation. arxiv:2206.10128"},{"key":"e_1_3_2_1_55_1","unstructured":"Shengyao Zhuang Houxing Ren Linjun Shou Jian Pei Ming Gong Guido Zuccon and Daxin Jiang. 2023b. Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation. arxiv:2206.10128"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3729973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:33:37Z","timestamp":1755887617000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3729973"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":55,"alternative-id":["10.1145\/3726302.3729973","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3729973","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}