{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:59Z","timestamp":1786120859825,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"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":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818454","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"7600-7611","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0883-3678","authenticated-orcid":false,"given":"Mingzhe","family":"Li","sequence":"first","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7674-7545","authenticated-orcid":false,"given":"Jing","family":"Xiang","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7153-4244","authenticated-orcid":false,"given":"Enguo","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8742-7708","authenticated-orcid":false,"given":"Lang","family":"Gao","sequence":"additional","affiliation":[{"name":"MBZUAI, ByteDance, Masdar City, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7589-3257","authenticated-orcid":false,"given":"Tai","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9964-6298","authenticated-orcid":false,"given":"Qishen","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3574-5665","authenticated-orcid":false,"given":"Xiangliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6633-0796","authenticated-orcid":false,"given":"Xiuying","family":"Chen","sequence":"additional","affiliation":[{"name":"MBZUAI, Masdar city, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICEC.1994.350042"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.464"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1547"},{"key":"e_1_3_2_1_4_1","volume-title":"Controllable text generation with language constraints. arXiv preprint arXiv:2212.10466","author":"Chen Howard","year":"2022","unstructured":"Howard Chen, Huihan Li, Danqi Chen, and Karthik Narasimhan. 2022. Controllable text generation with language constraints. arXiv preprint arXiv:2212.10466 (2022)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09866-x"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 9147-9164","author":"Dong Wenjie","year":"2025","unstructured":"Wenjie Dong, Sirong Chen, and Yan Yang. 2025. Protod: Proactive task-oriented dialogue system based on large language model. In Proceedings of the 31st International Conference on Computational Linguistics. 9147-9164."},{"key":"e_1_3_2_1_7_1","volume-title":"Kto: Model alignment as prospect theoretic optimization. ICML","author":"Ethayarajh Kawin","year":"2024","unstructured":"Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, and Douwe Kiela. 2024. Kto: Model alignment as prospect theoretic optimization. ICML (2024)."},{"key":"e_1_3_2_1_8_1","unstructured":"Yihao Feng Shentao Yang Shujian Zhang Jianguo Zhang Caiming Xiong Mingyuan Zhou and Huan Wang. 2023. Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-Oriented Dialogue Systems. In ICLR."},{"key":"e_1_3_2_1_9_1","volume-title":"V9, 2","author":"Hansen Nikolaus","year":"2001","unstructured":"Nikolaus Hansen and Andreas Ostermeier. 2001. Completely derandomized self-adaptation in evolution strategies. Evolutionary computation, V9, 2 (2001), 159-195."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21320"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1201\/b10451"},{"key":"e_1_3_2_1_12_1","volume-title":"V33","author":"Hosseini-Asl Ehsan","year":"2020","unstructured":"Ehsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz, and Richard Socher. 2020. A simple language model for task-oriented dialogue. Advances in Neural Information Processing Systems, V33 (2020), 20179-20191."},{"key":"e_1_3_2_1_13_1","volume-title":"Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, and Rosalind Picard.","author":"Jaques Natasha","year":"2019","unstructured":"Natasha Jaques, Asma Ghandeharioun, Judy Hanwen Shen, Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, and Rosalind Picard. 2019. Way off-policy batch deep reinforcement learning of implicit human preferences in dialog. arXiv preprint arXiv:1907.00456 (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"Oya Deniz Beyan, and Zeyd Boukhers","author":"Kong Lingxiao","year":"2025","unstructured":"Lingxiao Kong, Cong Yang, Susanne Neufang, Oya Deniz Beyan, and Zeyd Boukhers. 2025. EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning. arXiv preprint arXiv:2505.02579 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1347-y"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning. PMLR, 26874-26901","author":"Lee Harrison","year":"2024","unstructured":"Harrison Lee, Samrat Phatale, Hassan Mansoor, Thomas Mesnard, Johan Ferret, Kellie Ren Lu, Colton Bishop, Ethan Hall, Victor Carbune, Abhinav Rastogi, et al., 2024. RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback. In International Conference on Machine Learning. PMLR, 26874-26901."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1094"},{"key":"e_1_3_2_1_18_1","unstructured":"Jiwei Li Will Monroe Tianlin Shi Sebastien Jean Alan Ritter and Dan Jurafsky. 2016b. Deep reinforcement learning for dialogue generation. In EMNLP."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635813"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1081"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-072-4_096"},{"key":"e_1_3_2_1_22_1","volume-title":"Dynamic reward adjustment in multi-reward reinforcement learning for counselor reflection generation. COLING","author":"Min Do June","year":"2024","unstructured":"Do June Min, Veronica Perez-Rosas, Kenneth Resnicow, and Rada Mihalcea. 2024. Dynamic reward adjustment in multi-reward reinforcement learning for counselor reflection generation. COLING (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_24_1","volume-title":"And Real-Time Engagement (November 26","author":"Patil Dimple","year":"2024","unstructured":"Dimple Patil. 2024. Artificial intelligence in retail and e-commerce: Enhancing customer experience through personalization, predictive analytics, and real-time engagement. Predictive Analytics, And Real-Time Engagement (November 26, 2024) (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1237"},{"key":"e_1_3_2_1_26_1","volume-title":"V36","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems, V36 (2023), 53728-53741."},{"key":"e_1_3_2_1_27_1","volume-title":"V15, 1","author":"Reddy Vijay Mallik","year":"2024","unstructured":"Vijay Mallik Reddy and Lakshmi Nivas Nalla. 2024. Personalization in e-commerce marketing: leveraging big data for tailored consumer engagement. Revista de Inteligencia Artificial en Medicina, V15, 1 (2024), 691-725."},{"key":"e_1_3_2_1_28_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","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_1_29_1","unstructured":"Abigail See Stephen Roller Douwe Kiela and Jason Weston. 2019. What makes a good conversation? How controllable attributes affect human judgments. In NAACL."},{"key":"e_1_3_2_1_30_1","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y. K. Li Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.295"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6417"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1379"},{"key":"e_1_3_2_1_34_1","volume-title":"V33","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. Advances in neural information processing systems, V33 (2020), 3008-3021."},{"key":"e_1_3_2_1_35_1","unstructured":"Pei-Hao Su Milica Gasic Nikola Mrksic Lina M Rojas-Barahona Stefan Ultes David Vandyke Tsung-Hsien Wen and Steve Young. 2016. On-line active reward learning for policy optimisation in spoken dialogue systems. In ACL."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.708"},{"key":"e_1_3_2_1_37_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, V35 (2022), 24824-24837."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.152"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.338"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17674"},{"key":"e_1_3_2_1_41_1","volume-title":"Rrhf: Rank responses to align language models with human feedback. Advances in Neural Information Processing Systems, V36","author":"Yuan Hongyi","year":"2023","unstructured":"Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, and Fei Huang. 2023. Rrhf: Rank responses to align language models with human feedback. Advances in Neural Information Processing Systems, V36 (2023), 10935-10950."},{"key":"e_1_3_2_1_42_1","volume-title":"UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems. arXiv preprint arXiv:2401.09034","author":"Zhang Changshuo","year":"2024","unstructured":"Changshuo Zhang, Sirui Chen, Xiao Zhang, Sunhao Dai, Weijie Yu, and Jun Xu. 2024. UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems. arXiv preprint arXiv:2401.09034 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Saizheng Zhang Emily Dinan Jack Urbanek Arthur Szlam Douwe Kiela and Jason Weston. 2018. Personalizing dialogue agents: I have a dog do you have pets too?. In ACL.","DOI":"10.18653\/v1\/P18-1205"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.891"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1692-3"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:31:29Z","timestamp":1786066289000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":45,"alternative-id":["10.1145\/3770855.3818454","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818454","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}