{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:08:46Z","timestamp":1785503326290,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2027,4,20]],"date-time":"2027-04-20T00:00:00Z","timestamp":1808179200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation (NSF) Division of Computer and Network Systems","award":["CNS-2431504"],"award-info":[{"award-number":["CNS-2431504"]}]},{"name":"National Science Foundation (NSF) Division of Computer and Network Systems","award":["CNS-2402862"],"award-info":[{"award-number":["CNS-2402862"]}]},{"name":"National Science Foundation (NSF)","award":["FAIN-2132573"],"award-info":[{"award-number":["FAIN-2132573"]}]},{"name":"Army Research Office","award":["W911NF-23-1-0088"],"award-info":[{"award-number":["W911NF-23-1-0088"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3785679","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"2806-2817","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LitBench: A Graph-Centric Large Language Model Benchmarking Tool For Literature Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2427-3240","authenticated-orcid":false,"given":"Andreas","family":"Varvarigos","sequence":"first","affiliation":[{"name":"Yale University, New Haven, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3436-7068","authenticated-orcid":false,"given":"Ali","family":"Maatouk","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5640-2020","authenticated-orcid":false,"given":"Jiasheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4345-6003","authenticated-orcid":false,"given":"Ngoc","family":"Bui","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0909-4620","authenticated-orcid":false,"given":"Jialin","family":"Chen","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0932-774X","authenticated-orcid":false,"given":"Leandros","family":"Tassiulas","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5856-5229","authenticated-orcid":false,"given":"Rex","family":"Ying","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, Connecticut, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_2_1","volume-title":"SciBERT: A pretrained language model for scientific text. arXiv preprint arXiv:1903.10676","author":"Beltagy Iz","year":"2019","unstructured":"Iz Beltagy, Kyle Lo, and Arman Cohan. 2019. SciBERT: A pretrained language model for scientific text. arXiv preprint arXiv:1903.10676 (2019)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29723"},{"key":"e_1_3_2_2_4_1","volume-title":"LEGAL-BERT: The muppets straight out of law school. arXiv preprint arXiv:2010.02559","author":"Chalkidis Ilias","year":"2020","unstructured":"Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, Nikolaos Aletras, and Ion Androutsopoulos. 2020. LEGAL-BERT: The muppets straight out of law school. arXiv preprint arXiv:2010.02559 (2020)."},{"key":"e_1_3_2_2_5_1","volume-title":"Madeleine Van Zuylen, and Field Cady","author":"Cohan Arman","year":"2019","unstructured":"Arman Cohan, Waleed Ammar, Madeleine Van Zuylen, and Field Cady. 2019. Structural scaffolds for citation intent classification in scientific publications. arXiv preprint arXiv:1904.01608 (2019)."},{"key":"e_1_3_2_2_6_1","volume-title":"Specter: Document-level representation learning using citation-informed transformers. arXiv preprint arXiv:2004.07180","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. arXiv preprint arXiv:2004.07180 (2020)."},{"key":"e_1_3_2_2_7_1","volume-title":"Malik Boudiaf, Dominic Culver, Rui Melo, Caio Corro, Andre F. T. Martins, Fabrizio Esposito, Vera L\u00facia Raposo, Sofia Morgado, and Michael Desa.","author":"Colombo Pierre","year":"2024","unstructured":"Pierre Colombo, Telmo Pessoa Pires, Malik Boudiaf, Dominic Culver, Rui Melo, Caio Corro, Andre F. T. Martins, Fabrizio Esposito, Vera L\u00facia Raposo, Sofia Morgado, and Michael Desa. 2024. SaulLM-7B: A pioneering Large Language Model for Law. arXiv:2403.03883 [cs.CL] https:\/\/arxiv.org\/abs\/2403.03883"},{"key":"e_1_3_2_2_8_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_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0308041"},{"key":"e_1_3_2_2_11_1","volume-title":"Clinicalbert: Modeling clinical notes and predicting hospital readmission. arXiv preprint arXiv:1904.05342","author":"Huang Kexin","year":"2019","unstructured":"Kexin Huang, Jaan Altosaar, and Rajesh Ranganath. 2019. Clinicalbert: Modeling clinical notes and predicting hospital readmission. arXiv preprint arXiv:1904.05342 (2019)."},{"key":"e_1_3_2_2_12_1","volume-title":"Hannaneh Hajishirzi, and Iz Beltagy.","author":"Jain Sarthak","year":"2020","unstructured":"Sarthak Jain, Madeleine Van Zuylen, Hannaneh Hajishirzi, and Iz Beltagy. 2020. SciREX: A challenge dataset for document-level information extraction. arXiv preprint arXiv:2005.00512 (2020)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00028"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313700"},{"key":"e_1_3_2_2_15_1","volume-title":"Tathagata Raha, Nada Saadi, Hamza Javed, Svetlana Maslenkova, Nasir Hayat, Ronnie Rajan, and Shadab Khan.","author":"Kanithi Praveen K","year":"2024","unstructured":"Praveen K Kanithi, Cl\u00e9ment Christophe, Marco AF Pimentel, Tathagata Raha, Nada Saadi, Hamza Javed, Svetlana Maslenkova, Nasir Hayat, Ronnie Rajan, and Shadab Khan. 2024. MEDIC: Towards a Comprehensive Framework for Evaluating LLMs in Clinical Applications. arXiv preprint arXiv:2409.07314 (2024)."},{"key":"e_1_3_2_2_16_1","volume-title":"Biomistral: A collection of open-source pretrained large language models for medical domains. arXiv preprint arXiv:2402.10373","author":"Labrak Yanis","year":"2024","unstructured":"Yanis Labrak, Adrien Bazoge, Emmanuel Morin, Pierre-Antoine Gourraud, Mickael Rouvier, and Richard Dufour. 2024a. Biomistral: A collection of open-source pretrained large language models for medical domains. arXiv preprint arXiv:2402.10373 (2024)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Yanis Labrak Adrien Bazoge Emmanuel Morin Pierre-Antoine Gourraud Mickael Rouvier and Richard Dufour. 2024b. BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains. arXiv:2402.10373 [cs.CL] https:\/\/arxiv.org\/abs\/2402.10373","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"e_1_3_2_2_18_1","volume-title":"Synergizing knowledge graphs with large language models: a comprehensive review and future prospects. arXiv preprint arXiv:2407.18470","author":"Li DaiFeng","year":"2024","unstructured":"DaiFeng Li and Fan Xu. 2024. Synergizing knowledge graphs with large language models: a comprehensive review and future prospects. arXiv preprint arXiv:2407.18470 (2024)."},{"key":"e_1_3_2_2_19_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74-81. https:\/\/aclanthology.org\/W04-1013"},{"key":"e_1_3_2_2_20_1","unstructured":"Chen Ling Xujiang Zhao Jiaying Lu Chengyuan Deng Can Zheng Junxiang Wang Tanmoy Chowdhury Yun Li Hejie Cui Xuchao Zhang et al. 2023. Domain specialization as the key to make large language models disruptive: A comprehensive survey. arXiv preprint arXiv:2305.18703 (2023)."},{"key":"e_1_3_2_2_21_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_2_22_1","volume-title":"Fingpt: Democratizing internet-scale data for financial large language models. arXiv preprint arXiv:2307.10485","author":"Liu Xiao-Yang","year":"2023","unstructured":"Xiao-Yang Liu, Guoxuan Wang, Hongyang Yang, and Daochen Zha. 2023. Fingpt: Democratizing internet-scale data for financial large language models. arXiv preprint arXiv:2307.10485 (2023)."},{"key":"e_1_3_2_2_23_1","volume-title":"Mark Neumann, Rodney Kinney, and Dan S Weld.","author":"Lo Kyle","year":"2019","unstructured":"Kyle Lo, Lucy Lu Wang, Mark Neumann, Rodney Kinney, and Dan S Weld. 2019. S2ORC: The semantic scholar open research corpus. arXiv preprint arXiv:1911.02782 (2019)."},{"key":"e_1_3_2_2_24_1","volume-title":"Are Large Language Models True Healthcare Jacks-of-All-Trades? Benchmarking Across Health Professions Beyond Physician Exams. arXiv preprint arXiv:2406.11328","author":"Luo Zheheng","year":"2024","unstructured":"Zheheng Luo, Chenhan Yuan, Qianqian Xie, and Sophia Ananiadou. 2024. Are Large Language Models True Healthcare Jacks-of-All-Trades? Benchmarking Across Health Professions Beyond Physician Exams. arXiv preprint arXiv:2406.11328 (2024)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352100"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_2_27_1","volume-title":"OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts. arXiv preprint arXiv:2205.01833","author":"Priem Jason","year":"2022","unstructured":"Jason Priem, Heather Piwowar, and Richard Orr. 2022. OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts. arXiv preprint arXiv:2205.01833 (2022)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Sayar Ghosh Roy and Jiawei Han. 2024. ILCiteR: Evidence-grounded Interpretable Local Citation Recommendation. arXiv:2403.08737 [cs.IR]","DOI":"10.63317\/4j2msq9yo8o6"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL57899.2023.00020"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742839"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657775"},{"key":"e_1_3_2_2_32_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSR61664.2024.10679494"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"George Tsatsaronis Georgios Balikas Prodromos Malakasiotis Ioannis Partalas Matthias Zschunke Michael R Alvers Dirk Weissenborn Anastasia Krithara Sergios Petridis Dimitris Polychronopoulos et al. 2015. An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition. BMC bioinformatics Vol. 16 (2015) 1-28.","DOI":"10.1186\/s12859-015-0564-6"},{"key":"e_1_3_2_2_35_1","volume-title":"ClinicalGPT: large language models finetuned with diverse medical data and comprehensive evaluation. arXiv preprint arXiv:2306.09968","author":"Wang Guangyu","year":"2023","unstructured":"Guangyu Wang, Guoxing Yang, Zongxin Du, Longjun Fan, and Xiaohu Li. 2023. ClinicalGPT: large language models finetuned with diverse medical data and comprehensive evaluation. arXiv preprint arXiv:2306.09968 (2023)."},{"key":"e_1_3_2_2_36_1","volume-title":"Julia Anna Bingler, and Markus Leippold","author":"Webersinke Nicolas","year":"2021","unstructured":"Nicolas Webersinke, Mathias Kraus, Julia Anna Bingler, and Markus Leippold. 2021. Climatebert: A pretrained language model for climate-related text. arXiv preprint arXiv:2110.12010 (2021)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae045"},{"key":"e_1_3_2_2_38_1","unstructured":"Yong Xie Karan Aggarwal and Aitzaz Ahmad. 2023. Efficient Continual Pre-training for Building Domain Specific Large Language Models. arXiv:2311.08545 [cs.CL] https:\/\/arxiv.org\/abs\/2311.08545"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0755"},{"key":"e_1_3_2_2_40_1","unstructured":"Jiasheng Zhang Jialin Chen Ali Maatouk Ngoc Bui Qianqian Xie Leandros Tassiulas Jie Shao Hua Xu and Rex Ying. 2024. LitFM: A Retrieval Augmented Structure-aware Foundation Model For Citation Graphs. arXiv preprint arXiv:2409.12177 (2024)."},{"key":"e_1_3_2_2_41_1","unstructured":"Tianyi Zhang Varsha Kishore Felix Wu Kilian Q. Weinberger and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. arXiv:1904.09675 [cs.CL] https:\/\/arxiv.org\/abs\/1904.09675"}],"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.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3785679","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3785679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:28:15Z","timestamp":1785500895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3785679"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":41,"alternative-id":["10.1145\/3770854.3785679","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3785679","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}