{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:13:24Z","timestamp":1775841204200,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792730","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:39Z","timestamp":1775771679000},"page":"2513-2523","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2366-5296","authenticated-orcid":false,"given":"Kaehyun","family":"Um","sequence":"first","affiliation":[{"name":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4252-6203","authenticated-orcid":false,"given":"KyuHwan","family":"Yeom","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4664-6880","authenticated-orcid":false,"given":"Haerim","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3838-706X","authenticated-orcid":false,"given":"Minyoung","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7958-224X","authenticated-orcid":false,"given":"Hyeongjun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1581-917X","authenticated-orcid":false,"given":"Kyong-Ho","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University, Seoul, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Dbpedia: A nucleus for a web of open data. In international semantic web conference","author":"Auer S\u00f6ren","year":"2007","unstructured":"S\u00f6ren Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary Ives. 2007. Dbpedia: A nucleus for a web of open data. In international semantic web conference. Springer, 722-735."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_3_2_1_3_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645563"},{"key":"e_1_3_2_1_5_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 e-prints (2024) arXiv-2407."},{"key":"e_1_3_2_1_6_1","volume-title":"Robert Osazuwa Ness, and Jonathan Larson","author":"Edge Darren","year":"2024","unstructured":"Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130 (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"Luke Friedman Sameer Ahuja David Allen Zhenning Tan Hakim Sidahmed Changbo Long Jun Xie Gabriel Schubiner Ajay Patel Harsh Lara et al. 2023. Leveraging large language models in conversational recommender systems. arXiv preprint arXiv:2305.07961 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441753"},{"key":"e_1_3_2_1_9_1","volume-title":"Adams Wei Yu, Xinying Song, and Denny Zhou.","author":"Huang Jie","year":"2023","unstructured":"Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2023. Large language models cannot self-correct reasoning yet. arXiv preprint arXiv:2310.01798 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Andrea Madotto, and Pascale Fung.","author":"Ji Ziwei","year":"2023","unstructured":"Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM computing surveys, Vol. 55, 12 (2023), 1-38."},{"key":"e_1_3_2_1_11_1","volume-title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph. In The Eleventh International Conference on Learning Representations.","author":"Jiang Jinhao","year":"2023","unstructured":"Jinhao Jiang, Kun Zhou, Xin Zhao, and Ji-Rong Wen. 2023. UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.594"},{"key":"e_1_3_2_1_13_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, Vol. 35 (2022), 22199-22213."},{"key":"e_1_3_2_1_14_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Li Mufei","year":"2025","unstructured":"Mufei Li, Siqi Miao, and Pan Li. 2025. Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714768"},{"key":"e_1_3_2_1_16_1","volume-title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. In The Twelfth International Conference on Learning Representations.","author":"Luo Linhao","year":"2024","unstructured":"Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2024. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","volume-title":"Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models. In Forty-second International Conference on Machine Learning.","author":"Luo Linhao","year":"2025","unstructured":"Linhao Luo, Zicheng Zhao, Gholamreza Haffari, Yuan-Fang Li, Chen Gong, and Shirui Pan. 2025. Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.856"},{"key":"e_1_3_2_1_19_1","first-page":"124198","article-title":"Simpo: Simple preference optimization with a reference-free reward","volume":"37","author":"Meng Yu","year":"2024","unstructured":"Yu Meng, Mengzhou Xia, and Danqi Chen. 2024. Simpo: Simple preference optimization with a reference-free reward. Advances in Neural Information Processing Systems, Vol. 37 (2024), 124198-124235.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_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_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352100"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.294"},{"key":"e_1_3_2_1_23_1","volume-title":"Direct preference optimization: Your language model is secretly a reward model. Advances in neural information processing systems","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, Vol. 36 (2023), 53728-53741."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCSW.2011.20"},{"key":"e_1_3_2_1_26_1","volume-title":"Retrieval augmentation reduces hallucination in conversation. arXiv preprint arXiv:2104.07567","author":"Shuster Kurt","year":"2021","unstructured":"Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval augmentation reduces hallucination in conversation. arXiv preprint arXiv:2104.07567 (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"Learning to summarize with human feedback. Advances in neural information processing systems","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, Vol. 33 (2020), 3008-3021."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1455"},{"key":"e_1_3_2_1_29_1","volume-title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. In The Twelfth International Conference on Learning Representations.","author":"Sun Jiashuo","year":"2024","unstructured":"Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel Ni, Heung-Yeung Shum, and Jian Guo. 2024. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1059"},{"key":"e_1_3_2_1_31_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_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599387"},{"key":"e_1_3_2_1_33_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, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_1_34_1","volume-title":"Retrieve-rewrite-answer: A kg-to-text enhanced llms framework for knowledge graph question answering. arXiv preprint arXiv:2309.11206","author":"Wu Yike","year":"2023","unstructured":"Yike Wu, Nan Hu, Sheng Bi, Guilin Qi, Jie Ren, Anhuan Xie, and Wei Song. 2023. Retrieve-rewrite-answer: A kg-to-text enhanced llms framework for knowledge graph question answering. arXiv preprint arXiv:2309.11206 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34747"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 201-206","author":"Richardson Matthew","year":"2016","unstructured":"Wen-tau Yih, Matthew Richardson, Christopher Meek, Ming-Wei Chang, and Jina Suh. 2016. The value of semantic parse labeling for knowledge base question answering. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 201-206."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.396"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:29:59Z","timestamp":1775838599000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":37,"alternative-id":["10.1145\/3774904.3792730","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792730","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}