{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:06:22Z","timestamp":1784138782807,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science Foundation","award":["IIS-2145411"],"award-info":[{"award-number":["IIS-2145411"]}]},{"name":"National Science Foundation CISE Graduate Fellowship","award":["2313998"],"award-info":[{"award-number":["2313998"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809925","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3715-3720","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["How Fine-Grained Should a RAG Benchmark Be? A Hierarchical Framework for Synthetic Question Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6761-1809","authenticated-orcid":false,"given":"Chase M.","family":"Fensore","sequence":"first","affiliation":[{"name":"Department of Computer Science, Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8875-176X","authenticated-orcid":false,"given":"Kaustubh","family":"Dhole","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6648-4164","authenticated-orcid":false,"given":"Jason","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3148-5448","authenticated-orcid":false,"given":"Eugene","family":"Agichtein","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9168-3916","authenticated-orcid":false,"given":"Joyce C.","family":"Ho","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531926"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Simone Filice Guy Horowitz David Carmel Zohar Karnin Liane Lewin-Eytan and Yoelle Maarek. 2025. Generating Diverse Q &A Benchmarks for RAG Evaluation with DataMorgana. arXiv:2501.12789 [cs] doi:10.48550\/arXiv.2501.12789","DOI":"10.48550\/arXiv.2501.12789"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000050"},{"key":"e_1_3_2_1_6_1","unstructured":"Jeffrey Ip and Kritin Vongthongsri. 2025. deepeval. https:\/\/github.com\/confident-ai\/deepeval original-date: 2023-08-10T05:35:04Z."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_2_1_8_1","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 Vol. 33 (2020) 9459-9474."},{"key":"e_1_3_2_1_9_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74-81."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.192"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482013"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0970"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.02252"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_2_1_17_1","unstructured":"Falcon-LLM Team. 2024. The Falcon 3 Family of Open Models. https:\/\/huggingface.co\/blog\/falcon3"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1953024"},{"key":"e_1_3_2_1_19_1","volume-title":"NIST","volume":"3","author":"Voorhees Ellen M.","year":"2000","unstructured":"Ellen M. Voorhees and D. M. Tice. 2000. The TREC-8 Question Answering Track Evaluation. NIST, Vol. 3 (May 2000). https:\/\/www.nist.gov\/publications\/trec-8-question-answering-track-evaluation Last Modified: 2017-02-17T13:34-05:00 Publisher: Ellen M. Voorhees, D M. Tice."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/11555261_12"},{"key":"e_1_3_2_1_21_1","volume-title":"Diversity Enhances an LLM's Performance in RAG and Long-context Task. arXiv preprint arXiv:2502.09017","author":"Wang Zhichao","year":"2025","unstructured":"Zhichao Wang, Bin Bi, Yanqi Luo, Sitaram Asur, and Claire Na Cheng. 2025. Diversity Enhances an LLM's Performance in RAG and Long-context Task. arXiv preprint arXiv:2502.09017 (2025)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1809.09600"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.365"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761382"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3805712.3809925","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:19:17Z","timestamp":1784135957000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":24,"alternative-id":["10.1145\/3805712.3809925","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809925","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}