{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:50:38Z","timestamp":1755795038924,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737432","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:04:26Z","timestamp":1754255066000},"page":"5619-5630","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Research"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2847-4071","authenticated-orcid":false,"given":"Junyong","family":"Lin","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9795-8968","authenticated-orcid":false,"given":"Lu","family":"Dai","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China and The Hong Kong University of Science and Technology, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0440-735X","authenticated-orcid":false,"given":"Ruiqian","family":"Han","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4344-7745","authenticated-orcid":false,"given":"Yijie","family":"Sui","sequence":"additional","affiliation":[{"name":"Institute of Tibetan Plateau Research, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6976-4212","authenticated-orcid":false,"given":"Ruilin","family":"Wang","sequence":"additional","affiliation":[{"name":"Lanzhou University, Lanzhou, Gansu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3756-2758","authenticated-orcid":false,"given":"Xingliang","family":"Sun","sequence":"additional","affiliation":[{"name":"Lanzhou University, Lanzhou, Gansu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0514-6287","authenticated-orcid":false,"given":"Qinglin","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute of Tibetan Plateau Research, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7456-7534","authenticated-orcid":false,"given":"Min","family":"Feng","sequence":"additional","affiliation":[{"name":"Institute of Tibetan Plateau Research, Chinese Academy of Sciences, Beijing, China and College of Resources and Environment, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4271-1567","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and The Hong Kong University of Science and Technology, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6016-6465","authenticated-orcid":false,"given":"Hui","family":"Xiong","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and The Hong Kong University of Science and Technology, Hong Kong SAR, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.840"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1620"},{"key":"e_1_3_2_2_3_1","volume-title":"Kerangka landasan untuk pembelajaran, pengajaran, dan asesmen (terjemahan Agung Prihantoro)","author":"Anderson Lorin W","year":"2001","unstructured":"Lorin W Anderson and David R Krathwohl. 2010. Kerangka landasan untuk pembelajaran, pengajaran, dan asesmen (terjemahan Agung Prihantoro). New York: Addition Wesley Longman.(buku asli diterbitkan tahun 2001) (2010)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1371"},{"key":"e_1_3_2_2_5_1","volume-title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216","author":"Chen Jianlv","year":"2024","unstructured":"Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)."},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Chen Ziru","year":"2025","unstructured":"Ziru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang, Botao Yu, Yifei Li, Zeyi Liao, Chen Wei, Zitong Lu, Vishal Dey, Mingyi Xue, Frazier N. Baker, Benjamin Burns, Daniel Adu-Ampratwum, Xuhui Huang, Xia Ning, Song Gao, Yu Su, and Huan Sun. 2025. ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.207"},{"key":"e_1_3_2_2_8_1","volume-title":"SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ixMBnOhFGd","author":"Dai Lu","year":"2025","unstructured":"Lu Dai, Yijie Xu, Jinhui Ye, Hao Liu, and Hui Xiong. 2025. SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ixMBnOhFGd"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635772"},{"volume-title":"Unified language model pre-training for natural language understanding and generation","author":"Dong Li","key":"e_1_3_2_2_10_1","unstructured":"Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, and Hsiao-Wuen Hon. 2019. Unified language model pre-training for natural language understanding and generation. Curran Associates Inc."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482166"},{"key":"e_1_3_2_2_12_1","unstructured":"Tianyu Gao Howard Yen Jiatong Yu and Danqi Chen. 2023. Enabling Large Language Models to Generate Text with Citations. In Empirical Methods in Natural Language Processing (EMNLP)."},{"key":"e_1_3_2_2_13_1","volume-title":"Question asking during tutoring. American educational research journal 31, 1","author":"Graesser Arthur C","year":"1994","unstructured":"Arthur C Graesser and Natalie K Person. 1994. Question asking during tutoring. American educational research journal 31, 1 (1994), 104-137."},{"key":"e_1_3_2_2_14_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_2_15_1","volume-title":"International conference on machine learning. PMLR, 3929-3938","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. Retrieval augmented language model pre-training. In International conference on machine learning. PMLR, 3929-3938."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772734"},{"key":"e_1_3_2_2_17_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_2_19_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459-9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_20_1","volume-title":"Arena learning: Build data flywheel for llms post-training via simulated chatbot arena. arXiv preprint arXiv:2407.10627","author":"Luo Haipeng","year":"2024","unstructured":"Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, Qingwei Lin, Jianguang Lou, Shifeng Chen, Yansong Tang, and Weizhu Chen. 2024. Arena learning: Build data flywheel for llms post-training via simulated chatbot arena. arXiv preprint arXiv:2407.10627 (2024)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.92"},{"key":"e_1_3_2_2_22_1","volume-title":"Guoqing Zheng, Shweti Mahajan, Dany Rouhana, Andres Codas, Yadong Lu, Wei-ge Chen, Olga Vrousgos, Corby Rosset, et al.","author":"Mitra Arindam","year":"2024","unstructured":"Arindam Mitra, Luciano Del Corro, Guoqing Zheng, Shweti Mahajan, Dany Rouhana, Andres Codas, Yadong Lu, Wei-ge Chen, Olga Vrousgos, Corby Rosset, et al. 2024. Agentinstruct: Toward generative teaching with agentic flows. arXiv preprint arXiv:2407.03502 (2024)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.468"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1145"},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Su Hongjin","year":"2025","unstructured":"Hongjin Su, Howard Yen, Mengzhou Xia, Weijia Shi, Niklas Muennighoff, Han-yu Wang, Haisu Liu, Quan Shi, Zachary S Siegel, Michael Tang, Ruoxi Sun, Jinsung Yoon, Sercan O Arik, Danqi Chen, and Tao Yu. 2025. BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_2_26_1","volume-title":"Hashimoto","author":"Taori Rohan","year":"2023","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. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_2_27_1","volume-title":"Galactica: A large language model for science. arXiv preprint arXiv:2211.09085","author":"Taylor Ross","year":"2022","unstructured":"Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. 2022. Galactica: A large language model for science. arXiv preprint arXiv:2211.09085 (2022)."},{"key":"e_1_3_2_2_28_1","volume-title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. arXiv:2104.08663 [cs.IR] https:\/\/arxiv.org\/abs\/2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models. arXiv:2104.08663 [cs.IR] https:\/\/arxiv.org\/abs\/2104.08663"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00475"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.573"},{"key":"e_1_3_2_2_31_1","first-page":"77013","article-title":"Evaluating open-qa evaluation","volume":"36","author":"Wang Cunxiang","year":"2023","unstructured":"Cunxiang Wang, Sirui Cheng, Qipeng Guo, Yuanhao Yue, Bowen Ding, Zhikun Xu, Yidong Wang, Xiangkun Hu, Zheng Zhang, and Yue Zhang. 2023. Evaluating open-qa evaluation. Advances in Neural Information Processing Systems 36 (2023), 77013-77042.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_32_1","first-page":"38404","article-title":"Scientific document retrieval using multi-level aspect-based queries","volume":"36","author":"Wang Jianyou Andre","year":"2023","unstructured":"Jianyou Andre Wang, Kaicheng Wang, Xiaoyue Wang, Prudhviraj Naidu, Leon Bergen, and Ramamohan Paturi. 2023. Scientific document retrieval using multi-level aspect-based queries. Advances in Neural Information Processing Systems 36 (2023), 38404-38419.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_33_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"e_1_3_2_2_35_1","volume-title":"BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives. arXiv:2402.14151 [cs.IR] https:\/\/arxiv.org\/abs\/2402.14151","author":"Wang Xiaoyue","year":"2024","unstructured":"Xiaoyue Wang, Jianyou Wang, Weili Cao, Kaicheng Wang, Ramamohan Paturi, and Leon Bergen. 2024. BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives. arXiv:2402.14151 [cs.IR] https:\/\/arxiv.org\/abs\/2402.14151"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3613215"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"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\/3711896.3737432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T14:43:39Z","timestamp":1755355419000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":38,"alternative-id":["10.1145\/3711896.3737432","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737432","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"}}]}}