{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T14:18:44Z","timestamp":1777299524696,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62372264"],"award-info":[{"award-number":["62372264"]}]},{"name":"National Natural Science Foundation of China","award":["92467203"],"award-info":[{"award-number":["92467203"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792075","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"1852-1863","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["What Should I Cite? A RAG Benchmark for Academic Citation Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8012-100X","authenticated-orcid":false,"given":"Leqi","family":"Zheng","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1379-2005","authenticated-orcid":false,"given":"Jiajun","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3888-5719","authenticated-orcid":false,"given":"Canzhi","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2986-2574","authenticated-orcid":false,"given":"Chaokun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8813-2433","authenticated-orcid":false,"given":"Hongwei","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0817-4004","authenticated-orcid":false,"given":"Yuying","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1386-7662","authenticated-orcid":false,"given":"Yaoxin","family":"Mao","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2278-9977","authenticated-orcid":false,"given":"Shannan","family":"Yan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9111-3866","authenticated-orcid":false,"given":"Zixin","family":"Song","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4610-422X","authenticated-orcid":false,"given":"Zhiyuan","family":"Feng","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1163-1615","authenticated-orcid":false,"given":"Zhaolu","family":"Kang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6907-8289","authenticated-orcid":false,"given":"Zirong","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5918-3183","authenticated-orcid":false,"given":"Hang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9233-3827","authenticated-orcid":false,"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4238-1533","authenticated-orcid":false,"given":"Ziyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.840"},{"key":"e_1_3_2_1_2_1","volume-title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection.","author":"Asai Akari","year":"2024","unstructured":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-rag: Learning to retrieve, generate, and critique through self-reflection. (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Homophily and missing links in citation networks. EPJ Data Science 5, 7","author":"Ciotti Valerio","year":"2016","unstructured":"Valerio Ciotti, Moreno Bonaventura, Vincenzo Nicosia, Pietro Panzarasa, and Vito Latora. 2016. Homophily and missing links in citation networks. EPJ Data Science 5, 7 (2016)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Arman Cohan Waleed Ammar Madeleine van Zuylen and Field Cady. 2019. Structural Scaffolds for Citation Intent Classification in Scientific Publications. (2019) 3586--3596.","DOI":"10.18653\/v1\/N19-1361"},{"key":"e_1_3_2_1_5_1","volume-title":"Weld","author":"Cohan Arman","year":"2020","unstructured":"Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel S. Weld. 2020. SPECTER: Document-level Representation Learning using Citation-informed Transformers. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2270--2282."},{"key":"e_1_3_2_1_6_1","volume-title":"From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130","author":"Edge Darren","year":"2024","unstructured":"Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, 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":"Zhiyuan Feng Zhaolu Kang Qijie Wang Zhiying Du Jiongrui Yan Shubin Shi Chengbo Yuan Huizhi Liang Yu Deng Qixiu Li et al. 2025. Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes. arXiv preprint arXiv:2510.19400 (2025)."},{"key":"e_1_3_2_1_8_1","unstructured":"Tianyu Gao Xingcheng Yao and Danqi Chen. 2021. SimCSE: Simple contrastive learning of sentence embeddings. (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Tianyu Gao Howard Yen Jiatong Yu and Danqi Chen. 2023. Enabling Large Language Models to Generate Text with Citations. (2023) 6465--6488.","DOI":"10.18653\/v1\/2023.emnlp-main.398"},{"key":"e_1_3_2_1_10_1","unstructured":"Yingjie He Zhaolu Kang Kehan Jiang Qianyuan Zhang Jiachen Qian Chunlei Meng Yujie Feng Yuan Wang Jiabao Dou Aming Wu et al. 2026. How Order-Sensitive Are LLMs? OrderProbe for Deterministic Structural Reconstruction. arXiv preprint arXiv:2601.08626 (2026)."},{"key":"e_1_3_2_1_11_1","volume-title":"Integrating explanation and prediction in computational social science. Nature 595, 7866","author":"Hofman Jake M.","year":"2021","unstructured":"Jake M. Hofman, Duncan J. Watts, Susan Athey, Filiz Garip, Thomas L. Griffiths, Jon Kleinberg, Helen Margetts, Sendhil Mullainathan, Matthew J. Salganik, Simine Vazire, Alessandro Vespignani, and Tal Yarkoni. 2021. Integrating explanation and prediction in computational social science. Nature 595, 7866 (2021), 181--188."},{"key":"e_1_3_2_1_12_1","unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Keming Lu et al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Gautier Izacard and Edouard Grave. 2021. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. (2021).","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_2_1_14_1","volume-title":"Sung Ju Hwang, and Jong C Park","author":"Jeong Soyeong","year":"2024","unstructured":"Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C Park. 2024. Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity. (2024), 7029--7043."},{"key":"e_1_3_2_1_15_1","unstructured":"Zhaolu Kang Junhao Gong Wenqing Hu Shuo Yin Kehan Jiang Zhicheng Fang Yingjie He Chunlei Meng Rong Fu Dongyang Chen et al. 2026. QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models. arXiv preprint arXiv:2601.08689 (2026)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-023-00352-7"},{"key":"e_1_3_2_1_17_1","volume-title":"Computational Social Science. Science 323, 5915","author":"Lazer David","year":"2009","unstructured":"David Lazer, Alex Pentland, Lada Adamic, Sinan Aral, Albert-L\u00e1szlo Barab\u00e1si, Devon Brewer, Nicholas Christakis, Noshir Contractor, James Fowler, Myron Gutmann, Tony Jebara, Gary King, Michael Macy, Deb Roy, and Marshall Van Alstyne. 2009. Computational Social Science. Science 323, 5915 (2009), 721--723."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Kenton Lee Ming-Wei Chang and Kristina Toutanova. 2019. Latent retrieval for weakly supervised open domain question answering. (2019) 6086--6096.","DOI":"10.18653\/v1\/P19-1612"},{"key":"e_1_3_2_1_19_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal et al. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"CapGeo: A Caption-Assisted Approach to Geometric Reasoning. arXiv preprint arXiv:2510.09302","author":"Li Yuying","year":"2025","unstructured":"Yuying Li, Siyi Qian, Hao Liang, Leqi Zheng, Ruichuan An, Yongzhen Guo, and Wentao Zhang. 2025. CapGeo: A Caption-Assisted Approach to Geometric Reasoning. arXiv preprint arXiv:2510.09302 (2025)."},{"key":"e_1_3_2_1_21_1","unstructured":"Jacob Menick Maja Trebacz Vladimir Mikulik John Aslanides Francis Song et al. 2022. Teaching language models to support answers with verified quotes. arXiv preprint arXiv:2203.11147 (2022)."},{"key":"e_1_3_2_1_22_1","unstructured":"Reiichiro Nakano Jacob Hilton Suchir Balaji Jeff Wu Long Ouyang et al. 2021. WebGPT: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021)."},{"key":"e_1_3_2_1_23_1","unstructured":"Hongjin Qian Yutao Zhu Zhicheng Dou Haoqi Gu Xinyu Zhang et al. 2023. WebBrain: Learning to generate factually correct articles for queries by grounding on large web corpus. arXiv preprint arXiv:2304.04358 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Yujia Qin Zihan Cai Dian Jin Lan Yan Shihao Liang Kunlun Zhu Yankai Lin Xu Han Ning Ding Huadong Wang et al. 2023. WebCPM: Interactive Web Search for Chinese Long-form Question Answering. (2023).","DOI":"10.18653\/v1\/2023.acl-long.499"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00486"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. (2019).","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_27_1","volume-title":"Including Structured Full-Text and Citation Network. In 2023 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). IEEE Computer Society, 66--70","author":"Saier Tarek","year":"2023","unstructured":"Tarek Saier, Johan Krause, and Michael F\u00e4rber. 2023. unarXive 2022: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network. In 2023 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). IEEE Computer Society, 66--70."},{"key":"e_1_3_2_1_28_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. (2020). arXiv:1909.08053 [cs.CL]"},{"key":"e_1_3_2_1_29_1","volume-title":"Qwen3-coder: Agentic coding in the world. Blog post","author":"Team Qwen","year":"2025","unstructured":"Qwen Team. 2025. Qwen3-coder: Agentic coding in the world. Blog post (2025)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Simone Teufel Jean Carletta and Marc Moens. 1999. An annotation scheme for discourse-level argumentation in research articles. (1999) 110--117.","DOI":"10.3115\/977035.977051"},{"key":"e_1_3_2_1_31_1","volume-title":"REASONS: A benchmark for REtrieval and Automated citationS Of scieNtific Sentences using Public and Proprietary LLMs. arXiv preprint arXiv:2405.02228","author":"Tilwani Deepa","year":"2024","unstructured":"Deepa Tilwani, Yash Saxena, Ali Mohammadi, Edward Raff, Amit Sheth, Srinivasan Parthasarathy, and Manas Gaur. 2024. REASONS: A benchmark for REtrieval and Automated citationS Of scieNtific Sentences using Public and Proprietary LLMs. arXiv preprint arXiv:2405.02228 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"A comprehensive survey of hallucination mitigation techniques in large language models. arXiv preprint arXiv:2401.01313","author":"Tonmoy SM","year":"2024","unstructured":"SM Tonmoy, SM Zaman, Vinija Jain, Anku Rani, Vipula Rawte, Aman Chadha, and Amitava Das. 2024. A comprehensive survey of hallucination mitigation techniques in large language models. arXiv preprint arXiv:2401.01313 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Harsh Trivedi Niranjan Balasubramanian Tushar Khot and Ashish Sabharwal. 2023. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. (2023) 10014--10037.","DOI":"10.18653\/v1\/2023.acl-long.557"},{"key":"e_1_3_2_1_34_1","volume-title":"Audio-Visual World Models: Towards Multisensory Imagination in Sight and Sound. arXiv preprint arXiv:2512.00883","author":"Wang Jiahua","year":"2025","unstructured":"Jiahua Wang, Shannan Yan, Leqi Zheng, Jialong Wu, and Yaoxin Mao. 2025. Audio-Visual World Models: Towards Multisensory Imagination in Sight and Sound. arXiv preprint arXiv:2512.00883 (2025)."},{"key":"e_1_3_2_1_35_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Haopeng Zhang Xiao Liu and Jiawei Zhang. 2023. Contrastive Hierarchical Discourse Graph for Scientific Document Summarization (CHANGES). (2023).","DOI":"10.18653\/v1\/2023.codi-1.4"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3769813"},{"key":"e_1_3_2_1_38_1","volume-title":"Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning. arXiv preprint arXiv:2601.13384","author":"Zhang Jiajun","year":"2026","unstructured":"Jiajun Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang, Yuheng Jing, Zeyao Ma, Tianyi Bai, Zilei Wang, Qiang Liu, Liang Wang, et al. 2026. From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning. arXiv preprint arXiv:2601.13384 (2026)."},{"key":"e_1_3_2_1_39_1","volume-title":"PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization. arXiv preprint arXiv:2511.00010","author":"Zhang Jiajun","year":"2025","unstructured":"Jiajun Zhang, Jianke Zhang, Zeyu Cui, Jiaxi Yang, Lei Zhang, Binyuan Hui, Qiang Liu, Zilei Wang, Liang Wang, and Junyang Lin. 2025. PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization. arXiv preprint arXiv:2511.00010 (2025)."},{"key":"e_1_3_2_1_40_1","unstructured":"Lei Zhang Mouxiang Chen Ruisheng Cao Jiawei Chen Fan Zhou Yiheng Xu Jiaxi Yang Liang Chen Changwei Luo Kai Zhang et al. 2026. MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era. arXiv preprint arXiv:2601.07526 (2026)."},{"key":"e_1_3_2_1_41_1","volume-title":"Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176","author":"Zhang Yanzhao","year":"2025","unstructured":"Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al. 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176 (2025)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.61"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729900"},{"key":"e_1_3_2_1_44_1","volume-title":"Negative Feedback Really Matters: Signed Dual-Channel Graph Contrastive Learning Framework for Recommendation. In The Thirty-ninth Annual Conference on Neural Information Processing Systems.","author":"Zheng Leqi","year":"2025","unstructured":"Leqi Zheng, Chaokun Wang, Zixin Song, Cheng Wu, Shannan Yan, Jiajun Zhang, and Ziyang Liu. 2025. Negative Feedback Really Matters: Signed Dual-Channel Graph Contrastive Learning Framework for Recommendation. In The Thirty-ninth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_45_1","volume-title":"Deepresearcher: Scaling deep research via reinforcement learning in real-world environments. arXiv preprint arXiv:2504.03160","author":"Zheng Yuxiang","year":"2025","unstructured":"Yuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai, Lyumanshan Ye, Pengrui Lu, and Pengfei Liu. 2025. Deepresearcher: Scaling deep research via reinforcement learning in real-world environments. arXiv preprint arXiv:2504.03160 (2025)."}],"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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T13:29:55Z","timestamp":1777296595000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792075"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":45,"alternative-id":["10.1145\/3774904.3792075","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792075","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"}}]}}