{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:21:14Z","timestamp":1765502474279,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761540","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T01:03:42Z","timestamp":1762563822000},"page":"5879-5887","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6495-7472","authenticated-orcid":false,"given":"Zhijie","family":"Lin","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7726-3644","authenticated-orcid":false,"given":"Zhuofeng","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0839-1037","authenticated-orcid":false,"given":"Chenglei","family":"Dai","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2195-0553","authenticated-orcid":false,"given":"Wentian","family":"Bao","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Sceience, Independent, New York, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7078-8257","authenticated-orcid":false,"given":"Shuai","family":"Lin","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0847-7464","authenticated-orcid":false,"given":"Enyun","family":"Yu","sequence":"additional","affiliation":[{"name":"Independent, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8398-9028","authenticated-orcid":false,"given":"Haoxiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2648-9989","authenticated-orcid":false,"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. {TensorFlow}: a system for {Large-Scale} machine learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16). 265--283."},{"key":"e_1_3_2_1_2_1","volume-title":"Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, et al.","author":"Abdin Marah","year":"2024","unstructured":"Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan, Jyoti Aneja, Ahmed Awadallah, Hany Awadalla, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Harkirat Behl, et al. 2024. Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209985"},{"key":"e_1_3_2_1_5_1","unstructured":"Rohan Anil Andrew M Dai Orhan Firat Melvin Johnson Dmitry Lepikhin Alexandre Passos Siamak Shakeri Emanuel Taropa Paige Bailey Zhifeng Chen et al. 2023. Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)."},{"key":"e_1_3_2_1_6_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Xiyang Luo, Alan Mackey, and Ofer Meshi.","author":"Bello Irwan","year":"2018","unstructured":"Irwan Bello, Sayali Kulkarni, Sagar Jain, Craig Boutilier, Ed Chi, Elad Eban, Xiyang Luo, Alan Mackey, and Ofer Meshi. 2018. Seq2Slate: Re-ranking and slate optimization with RNNs. arXiv preprint arXiv:1810.02019 (2018)."},{"key":"e_1_3_2_1_8_1","first-page":"324","article-title":"Rank Analysis of Incomplete Block Designs","volume":"39","author":"Bradley Ralph Allan","year":"1952","unstructured":"Ralph Allan Bradley and Milton E. Terry. 1952. Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons. Biometrika 39 (1952), 324.","journal-title":"I. The Method of Paired Comparisons. Biometrika"},{"key":"e_1_3_2_1_9_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. NeurIPS (2020)."},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24, 240 (2023), 1--113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_11_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_13_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Revisit recommender system in the permutation prospective. arXiv preprint arXiv:2102.12057","author":"Feng Yufei","year":"2021","unstructured":"Yufei Feng, Yu Gong, Fei Sun, Junfeng Ge, and Wenwu Ou. 2021. Revisit recommender system in the permutation prospective. arXiv preprint arXiv:2102.12057 (2021)."},{"key":"e_1_3_2_1_15_1","volume-title":"GRN: Generative Rerank Network for Context-wise Recommendation. arXiv preprint arXiv:2104.00860","author":"Feng Yufei","year":"2021","unstructured":"Yufei Feng, Binbin Hu, Yu Gong, Fei Sun, Qingwen Liu, and Wenwu Ou. 2021. GRN: Generative Rerank Network for Context-wise Recommendation. arXiv preprint arXiv:2104.00860 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714922"},{"key":"e_1_3_2_1_17_1","volume-title":"Baptiste Rozi\u00e8re, David Lopez-Paz, and Gabriel Synnaeve.","author":"Gloeckle Fabian","year":"2024","unstructured":"Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozi\u00e8re, David Lopez-Paz, and Gabriel Synnaeve. 2024. Better & faster large language models via multi-token prediction. arXiv preprint arXiv:2404.19737 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557065"},{"key":"e_1_3_2_1_19_1","volume-title":"Victor OK Li, and Richard Socher","author":"Gu Jiatao","year":"2017","unstructured":"Jiatao Gu, James Bradbury, Caiming Xiong, Victor OK Li, and Richard Socher. 2017. Non-autoregressive neural machine translation. arXiv preprint arXiv:1711.02281 (2017)."},{"key":"e_1_3_2_1_20_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","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 preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_21_1","volume-title":"Adam: A method for stochastic optimization. In ICLR.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICLR."},{"key":"e_1_3_2_1_22_1","volume-title":"Data-to-text generation with style imitation. arXiv preprint arXiv:1901.09501","author":"Lin Shuai","year":"2019","unstructured":"Shuai Lin,WentaoWang, Zichao Yang, Xiaodan Liang, Frank F Xu, Eric Xing, and Zhiting Hu. 2019. Data-to-text generation with style imitation. arXiv preprint arXiv:1901.09501 (2019)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17577"},{"key":"e_1_3_2_1_24_1","unstructured":"Xiao Lin Xiaokai Chen Chenyang Wang Hantao Shu Linfeng Song Biao Li et al. 2023. Discrete Conditional Diffusion for Reranking in Recommendation. arXiv preprint arXiv:2308.06982 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412222"},{"key":"e_1_3_2_1_26_1","volume-title":"Neural re-ranking in multi-stage recommender systems: A review. arXiv preprint arXiv:2202.06602","author":"Liu Weiwen","year":"2022","unstructured":"Weiwen Liu, Yunjia Xi, Jiarui Qin, Fei Sun, Bo Chen, Weinan Zhang, Rui Zhang, and Ruiming Tang. 2022. Neural re-ranking in multi-stage recommender systems: A review. arXiv preprint arXiv:2202.06602 (2022)."},{"key":"e_1_3_2_1_27_1","volume-title":"GPT-4 technical report. arXiv preprint arXiv:2303.08774","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Jan Leike, and Ryan J. Lowe.","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke E. Miller, Maddie Simens, Amanda Askell, PeterWelinder, Paul Francis Christiano, Jan Leike, and Ryan J. Lowe. 2022. Training language models to follow instructions with human feedback. In NeurIPS."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401104"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347000"},{"key":"e_1_3_2_1_31_1","unstructured":"Alec Radford. 2018. Improving language understanding by generative pretraining. (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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 ICML."},{"key":"e_1_3_2_1_33_1","unstructured":"Rafael Rafailov Archit Sharma Eric Mitchell Stefano Ermon Christopher D. Manning and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. In NeurIPS."},{"key":"e_1_3_2_1_34_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems 36","author":"Rafailov Rafael","year":"2024","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2024. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671645"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599886"},{"key":"e_1_3_2_1_37_1","volume-title":"Sequence to Sequence Learning with Neural Networks. arXiv preprint arXiv:1409.3215","author":"Sutskever I","year":"2014","unstructured":"I Sutskever. 2014. Sequence to Sequence Learning with Neural Networks. arXiv preprint arXiv:1409.3215 (2014)."},{"key":"e_1_3_2_1_38_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_40_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the ADKDD'17","author":"Fu Bin","year":"2017","unstructured":"RuoxiWang, Bin Fu, Gang Fu, and MingliangWang. 2017. Deep & cross network for ad click predictions. In Proceedings of the ADKDD'17. 1--7."},{"key":"e_1_3_2_1_43_1","volume-title":"Context-aware reranking with utility maximization for recommendation. arXiv preprint arXiv:2110.09059","author":"Xi Yunjia","year":"2021","unstructured":"Yunjia Xi, Weiwen Liu, Xinyi Dai, Ruiming Tang, Weinan Zhang, Qing Liu, Xiuqiang He, and Yong Yu. 2021. Context-aware reranking with utility maximization for recommendation. arXiv preprint arXiv:2110.09059 (2021)."},{"key":"e_1_3_2_1_44_1","unstructured":"Yang Yan Yihao Wang Chi Zhang Wenyuan Hou Kang Pan Xingkai Ren Zelun Wu Zhixin Zhai Enyun Yu Wenwu Ou et al. 2024. LLM4PR: Improving Post-Ranking in Search Engine with Large Language Models. arXiv preprint arXiv:2411.01178 (2024)."},{"key":"e_1_3_2_1_45_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 658--671","author":"Zhang Haobo","year":"2025","unstructured":"Haobo Zhang, Qiannan Zhu, and Zhicheng Dou. 2025. Enhancing Reranking for Recommendation with LLMs through User Preference Retrieval. In Proceedings of the 31st International Conference on Computational Linguistics. 658--671."},{"key":"e_1_3_2_1_47_1","volume-title":"Globally optimized mutual influence aware ranking in e-commerce search. arXiv preprint arXiv:1805.08524","author":"Zhuang Tao","year":"2018","unstructured":"Tao Zhuang, Wenwu Ou, and Zhirong Wang. 2018. Globally optimized mutual influence aware ranking in e-commerce search. arXiv preprint arXiv:1805.08524 (2018)."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:16:34Z","timestamp":1765502194000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":47,"alternative-id":["10.1145\/3746252.3761540","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761540","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}