{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:47:22Z","timestamp":1777873642604,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737222","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:07:39Z","timestamp":1754255259000},"page":"4966-4974","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FoodGPT: Reinforcement Post-Training of Large Language Models in the Food Delivery Domain"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2399-1153","authenticated-orcid":false,"given":"Jiang","family":"Wang","sequence":"first","affiliation":[{"name":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1921-3340","authenticated-orcid":false,"given":"Zhengxin","family":"Dong","sequence":"additional","affiliation":[{"name":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6508-8399","authenticated-orcid":false,"given":"Bing","family":"Bai","sequence":"additional","affiliation":[{"name":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8997-2585","authenticated-orcid":false,"given":"Guyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5372-6086","authenticated-orcid":false,"given":"Aiquan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Rajax Network Technology (ele.me), Alibaba Group, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0742-607X","authenticated-orcid":false,"given":"Guodong","family":"Cao","sequence":"additional","affiliation":[{"name":"Rajax Network Technology (ele.me), Alibaba Group, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_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_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401184"},{"key":"e_1_3_2_2_3_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_2_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17773"},{"key":"e_1_3_2_2_5_1","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys. org (accessed","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al., 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys. org (accessed 14 April 2023), Vol. 2, 3 (2023), 6."},{"key":"e_1_3_2_2_6_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_2_7_1","volume-title":"Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models. arXiv preprint arXiv:2304.01933(2023).","author":"Hu Zhiqiang","year":"2023","unstructured":"Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, and Roy Ka-Wei Lee. 2023. Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models. arXiv preprint arXiv:2304.01933(2023)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126583"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29820"},{"key":"e_1_3_2_2_10_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437(2024)."},{"key":"e_1_3_2_2_11_1","volume-title":"M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, et al.","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, et al., 2022. Crosslingual generalization through multitask finetuning. arXiv preprint arXiv:2211.01786(2022)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems Vol. 35 (2022) 27730-27744.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_2_13_1","unstructured":"Chester Palen-Michel Ruixiang Wang Yipeng Zhang David Yu Canran Xu and Zhe Wu. 2024. Investigating LLM Applications in E-Commerce. arXiv preprint arXiv:2408.12779(2024)."},{"key":"e_1_3_2_2_14_1","unstructured":"Bo Peng Xinyi Ling Ziru Chen Huan Sun and Xia Ning. 2024. eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale High-quality Instruction Data. arXiv preprint arXiv:2402.08831(2024)."},{"key":"e_1_3_2_2_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"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, Vol. 36 (2024)."},{"key":"e_1_3_2_2_16_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347(2017)."},{"key":"e_1_3_2_2_17_1","unstructured":"Karan Singhal Tao Tu Juraj Gottweis Rory Sayres Ellery Wulczyn Mohamed Amin Le Hou Kevin Clark Stephen R Pfohl Heather Cole-Lewis et al. 2025. Toward expert-level medical question answering with large language models. Nature Medicine(2025) 1-8."},{"key":"e_1_3_2_2_18_1","unstructured":"Rohan Taori Ishaan Gulrajani Tianyi Zhang Yann Dubois Xuechen Li Carlos Guestrin Percy Liang and Tatsunori B Hashimoto. 2023. Stanford alpaca: An instruction-following llama model."},{"key":"e_1_3_2_2_19_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971(2023).","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_2_20_1","unstructured":"Xinyu Wang Yong Jiang Nguyen Bach Tao Wang Zhongqiang Huang Fei Huang and Kewei Tu. 2021. Improving named entity recognition by external context retrieving and cooperative learning. arXiv preprint arXiv:2105.03654(2021)."},{"key":"e_1_3_2_2_21_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115(2024)."},{"key":"e_1_3_2_2_22_1","volume-title":"Fingpt: Open-source financial large language models. arXiv preprint arXiv:2306.06031(2023).","author":"Yang Hongyang","year":"2023","unstructured":"Hongyang Yang, Xiao-Yang Liu, and Christina Dan Wang. 2023. Fingpt: Open-source financial large language models. arXiv preprint arXiv:2306.06031(2023)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29917"},{"key":"e_1_3_2_2_24_1","unstructured":"Biao Zhang Zhongtao Liu Colin Cherry and Orhan Firat. 2024. When scaling meets llm finetuning: The effect of data model and finetuning method. arXiv preprint arXiv:2402.17193(2024)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358055"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:08:18Z","timestamp":1777572498000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":25,"alternative-id":["10.1145\/3711896.3737222","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737222","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}