{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T15:32:26Z","timestamp":1776094346043,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"NIH (National Institutes of Health)","doi-asserted-by":"publisher","award":["R01AG089806"],"award-info":[{"award-number":["R01AG089806"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2007716, 2007976, 1942594, 1907805"],"award-info":[{"award-number":["2007716, 2007976, 1942594, 1907805"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cisco Faculty Research Award"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3729920","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T14:55:26Z","timestamp":1752504926000},"page":"678-687","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3802-9039","authenticated-orcid":false,"given":"Yuntong","family":"Hu","sequence":"first","affiliation":[{"name":"Emory University, Atlanta, GA, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2909-1489","authenticated-orcid":false,"given":"Zhihan","family":"Lei","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8433-9499","authenticated-orcid":false,"given":"Zhongjie","family":"Dai","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5479-0622","authenticated-orcid":false,"given":"Allen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0295-0527","authenticated-orcid":false,"given":"Abhinav","family":"Angirekula","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9808-6020","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2648-9989","authenticated-orcid":false,"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1515\/bfp-2020-2042"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_1_3_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_1_4_1","volume-title":"Salient phrase aware dense retrieval: can a dense retriever imitate a sparse one? arXiv preprint arXiv:2110.06918","author":"Chen Xilun","year":"2021","unstructured":"Xilun Chen, Kushal Lakhotia, Barlas O\u011fuz, Anchit Gupta, Patrick Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta, and Wen-tau Yih. 2021. Salient phrase aware dense retrieval: can a dense retriever imitate a sparse one? arXiv preprint arXiv:2110.06918 (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"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","volume-title":"Language-agnostic BERT sentence embedding. arXiv preprint arXiv:2007.01852","author":"Feng Fangxiaoyu","year":"2020","unstructured":"Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, and Wei Wang. 2020. Language-agnostic BERT sentence embedding. arXiv preprint arXiv:2007.01852 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72113-8_10"},{"key":"e_1_3_2_1_9_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Rana Abdullah, Aida Usmanova, Ricardo Usbeck, Jennifer D'Souza, and S\u00f6ren Auer.","author":"Giglou Hamed Babaei","year":"2024","unstructured":"Hamed Babaei Giglou, Tilahun Abedissa Taffa, Rana Abdullah, Aida Usmanova, Ricardo Usbeck, Jennifer D'Souza, and S\u00f6ren Auer. 2024. Scholarly Question Answering using Large Language Models in the NFDI4DataScience Gateway. arXiv preprint arXiv:2406.07257 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"G-retriever: Retrieval-augmented generation for textual graph understanding and question answering. arXiv preprint arXiv:2402.07630","author":"He Xiaoxin","year":"2024","unstructured":"Xiaoxin He, Yijun Tian, Yifei Sun, Nitesh V Chawla, Thomas Laurent, Yann LeCun, Xavier Bresson, and Bryan Hooi. 2024. G-retriever: Retrieval-augmented generation for textual graph understanding and question answering. arXiv preprint arXiv:2402.07630 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"GRAG: Graph Retrieval-Augmented Generation. arXiv preprint arXiv:2405.16506","author":"Hu Yuntong","year":"2024","unstructured":"Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, and Liang Zhao. 2024. GRAG: Graph Retrieval-Augmented Generation. arXiv preprint arXiv:2405.16506 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data. arXiv preprint arXiv:2310.04944","author":"Hu Yuntong","year":"2023","unstructured":"Yuntong Hu, Zheng Zhang, and Liang Zhao. 2023. Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data. arXiv preprint arXiv:2310.04944 (2023)."},{"key":"e_1_3_2_1_14_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_1_15_1","volume-title":"Pubmedqa: A dataset for biomedical research question answering. arXiv preprint arXiv:1909.06146","author":"Jin Qiao","year":"2019","unstructured":"Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William W Cohen, and Xinghua Lu. 2019. Pubmedqa: A dataset for biomedical research question answering. arXiv preprint arXiv:1909.06146 (2019)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_18_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and MaxWelling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_19_1","volume-title":"Leveraging semantic and lexical matching to improve the recall of document retrieval systems: A hybrid approach. arXiv preprint arXiv:2010.01195","author":"Kuzi Saar","year":"2020","unstructured":"Saar Kuzi, Mingyang Zhang, Cheng Li, Michael Bendersky, and Marc Najork. 2020. Leveraging semantic and lexical matching to improve the recall of document retrieval systems: A hybrid approach. arXiv preprint arXiv:2010.01195 (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"Large Language Models for Scientific Question Answering: An Extensive Analysis of the SciQA Benchmark. In European Semantic Web Conference. Springer, 199--217","author":"Lehmann Jens","year":"2024","unstructured":"Jens Lehmann, Antonello Meloni, Enrico Motta, Francesco Osborne, Diego Reforgiato Recupero, Angelo Antonio Salatino, and Sahar Vahdati. 2024. Large Language Models for Scientific Question Answering: An Extensive Analysis of the SciQA Benchmark. In European Semantic Web Conference. Springer, 199--217."},{"key":"e_1_3_2_1_21_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_1_22_1","volume-title":"A survey on retrieval-augmented text generation. arXiv preprint arXiv:2202.01110","author":"Li Huayang","year":"2022","unstructured":"Huayang Li, Yixuan Su, Deng Cai, Yan Wang, and Lemao Liu. 2022. A survey on retrieval-augmented text generation. arXiv preprint arXiv:2202.01110 (2022)."},{"key":"e_1_3_2_1_23_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_24_1","volume-title":"PACIFIC SYMPOSIUM ON BIOCOMPUTING","author":"Lozano Alejandro","year":"2024","unstructured":"Alejandro Lozano, Scott L Fleming, Chia-Chun Chiang, and Nigam Shah. 2023. Clinfo. ai: An open-source retrieval-augmented large language model system for answering medical questions using scientific literature. In PACIFIC SYMPOSIUM ON BIOCOMPUTING 2024. World Scientific, 8--23."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_1_26_1","volume-title":"Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval. arXiv preprint arXiv:2401.04055","author":"Mandikal Priyanka","year":"2024","unstructured":"Priyanka Mandikal and Raymond Mooney. 2024. Sparse Meets Dense: A Hybrid Approach to Enhance Scientific Document Retrieval. arXiv preprint arXiv:2401.04055 (2024)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2024.0150379"},{"key":"e_1_3_2_1_28_1","volume-title":"Document expansion by query prediction. arXiv preprint arXiv:1904.08375","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Jimmy Lin, and Kyunghyun Cho. 2019. Document expansion by query prediction. arXiv preprint arXiv:1904.08375 (2019)."},{"key":"e_1_3_2_1_29_1","unstructured":"V\u00edt Novotny and Michal Stef\u00e1nik. 2022. Combining Sparse and Dense Information Retrieval.. In CLEF (Working Notes). 104--118."},{"key":"e_1_3_2_1_30_1","volume-title":"Sentence-BERT: Sentence Embeddings using Siamese BERTNetworks. arXiv preprint arXiv:1908.10084","author":"Reimers N","year":"2019","unstructured":"N Reimers. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERTNetworks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Stephen Robertson Hugo Zaragoza et al. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends\u00ae in Information Retrieval 3 4 (2009) 333--389.","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"key":"e_1_3_2_1_33_1","volume-title":"Masked label prediction: Unified message passing model for semisupervised classification. arXiv preprint arXiv:2009.03509","author":"Shi Yunsheng","year":"2020","unstructured":"Yunsheng Shi, Zhengjie Huang, Shikun Feng, Hui Zhong, Wenjin Wang, and Yu Sun. 2020. Masked label prediction: Unified message passing model for semisupervised classification. arXiv preprint arXiv:2009.03509 (2020)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00530"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3233\/FC-221513"},{"key":"e_1_3_2_1_36_1","unstructured":"Tilahun Abedissa Taffa and Ricardo Usbeck. 2023. Leveraging LLMs in Scholarly Knowledge Graph Question Answering.. In QALD\/SemREC@ ISWC."},{"key":"e_1_3_2_1_37_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Veli\u010dkovi\u0107 Petar","year":"2017","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_1_38_1","volume-title":"BioRAG: A RAG-LLM Framework for Biological Question Reasoning. arXiv preprint arXiv:2408.01107","author":"Wang Chengrui","year":"2024","unstructured":"Chengrui Wang, Qingqing Long, Xiao Meng, Xunxin Cai, Chengjun Wu, Zhen Meng, Xuezhi Wang, and Yuanchun Zhou. 2024. BioRAG: A RAG-LLM Framework for Biological Question Reasoning. arXiv preprint arXiv:2408.01107 (2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482007"},{"key":"e_1_3_2_1_40_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_1_41_1","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems 33 (2020), 5776--5788.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","volume-title":"Jing Liu, and Ji-Rong Wen.","author":"Wang Yuhao","year":"2024","unstructured":"Yuhao Wang, Ruiyang Ren, Junyi Li, Wayne Xin Zhao, Jing Liu, and Ji-Rong Wen. 2024. REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering. arXiv preprint arXiv:2402.17497 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"e_1_3_2_1_44_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_45_1","volume-title":"Evaluation of Retrieval-Augmented Generation: A Survey. arXiv preprint arXiv:2405.07437","author":"Yu Hao","year":"2024","unstructured":"Hao Yu, Aoran Gan, Kai Zhang, Shiwei Tong, Qi Liu, and Zhaofeng Liu. 2024. Evaluation of Retrieval-Augmented Generation: A Survey. arXiv preprint arXiv:2405.07437 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Cyril Zakka Rohan Shad Akash Chaurasia Alex R Dalal Jennifer L Kim Michael Moor Robyn Fong Curran Phillips Kevin Alexander Euan Ashley et al. 2024. Almanac-retrieval-augmented language models for clinical medicine. NEJM AI 1 2 (2024) AIoa2300068.","DOI":"10.1056\/AIoa2300068"},{"key":"e_1_3_2_1_47_1","volume-title":"Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473","author":"Zhao Penghao","year":"2024","unstructured":"Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang,Wentao Zhang, and Bin Cui. 2024. Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473 (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637870"},{"key":"e_1_3_2_1_49_1","volume-title":"Towards a unified multi-dimensional evaluator for text generation. arXiv preprint arXiv:2210.07197","author":"Zhong Ming","year":"2022","unstructured":"Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, Pengfei Liu, Chenguang Zhu, Heng Ji, and Jiawei Han. 2022. Towards a unified multi-dimensional evaluator for text generation. arXiv preprint arXiv:2210.07197 (2022)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3729920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:36:18Z","timestamp":1755887778000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3729920"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":49,"alternative-id":["10.1145\/3726302.3729920","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3729920","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}