{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:03:38Z","timestamp":1784138618318,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":50,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809752","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"723-733","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2247-3370","authenticated-orcid":false,"given":"Jia-Huei","family":"Ju","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-1535","authenticated-orcid":false,"given":"Eugene","family":"Yang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6430-2320","authenticated-orcid":false,"given":"Trevor","family":"Adriaanse","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9609-9505","authenticated-orcid":false,"given":"Suzan","family":"Verberne","sequence":"additional","affiliation":[{"name":"Leiden University, Leiden, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-880X","authenticated-orcid":false,"given":"Andrew","family":"Yates","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"MS MARCO: A human generated machine reading comprehension dataset. showeprint1611.09268","author":"Bajaj Payal","year":"2016","unstructured":"Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, et al., 2016. MS MARCO: A human generated machine reading comprehension dataset. showeprint1611.09268"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/290941.291025"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.431"},{"key":"e_1_3_2_1_4_1","unstructured":"Hung-Ting Chen Xiang Liu Shauli Ravfogel and Eunsol Choi. 2025. Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval. showeprint2511.02770"},{"key":"e_1_3_2_1_5_1","first-page":"2318","article-title":"M3-Embedding: Multi-Linguality, Multi-Functionality","author":"Chen Jianlyu","year":"2024","unstructured":"Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. In Findings of ACL. 2318-2335.","journal-title":"Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. In Findings of ACL."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390334.1390446"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1572114"},{"key":"e_1_3_2_1_8_1","volume-title":"Overview of the TREC 2021 deep learning track. showeprint2507","author":"Craswell Nick","year":"2025","unstructured":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos, and Jimmy Lin. 2025. Overview of the TREC 2021 deep learning track. showeprint2507.08191"},{"key":"e_1_3_2_1_9_1","volume-title":"Overview of the TREC 2024 NeuCLIR track. showeprint2509","author":"Dawn Lawrie","year":"2025","unstructured":"Lawrie Dawn, Macavaney Sean, Mayfield James, Mcnamee Paul, W Oard Douglas, Soldaini Luca, and Yang Eugene. 2025. Overview of the TREC 2024 NeuCLIR track. showeprint2509.14355"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657871"},{"key":"e_1_3_2_1_11_1","first-page":"1074","article-title":"Multi-News","author":"Fabbri Alexander","year":"2019","unstructured":"Alexander Fabbri, Irene Li, Tianwei She, Suyi Li, and Dragomir Radev. 2019. Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model. In Proc. of ACL. 1074-1084.","journal-title":"In Proc. of ACL."},{"key":"e_1_3_2_1_12_1","unstructured":"Naghmeh Farzi and Laura Dietz. 2024a. An exam-based evaluation approach beyond traditional relevance judgments. showeprint2402.00309"},{"key":"e_1_3_2_1_13_1","first-page":"175","article-title":"Pencils down! Automatic rubric-based evaluation of retrieve\/generate systems","author":"Farzi Naghmeh","year":"2024","unstructured":"Naghmeh Farzi and Laura Dietz. 2024b. Pencils down! Automatic rubric-based evaluation of retrieve\/generate systems. In Proc. of SIGIR. 175-184.","journal-title":"Proc. of SIGIR."},{"key":"e_1_3_2_1_14_1","first-page":"6465","article-title":"Enabling large language models to generate text with citations","author":"Gao Tianyu","year":"2023","unstructured":"Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen. 2023. Enabling large language models to generate text with citations. In Proc. of EMNLP. 6465-6488.","journal-title":"Proc. of EMNLP."},{"key":"e_1_3_2_1_15_1","first-page":"708","article-title":"Newsroom: A dataset of 1.3 million summaries with diverse extractive strategies","author":"Grusky Max","year":"2018","unstructured":"Max Grusky, Mor Naaman, and Yoav Artzi. 2018. Newsroom: A dataset of 1.3 million summaries with diverse extractive strategies. In Proc. of NAACL-HLT. 708-719.","journal-title":"Proc. of NAACL-HLT."},{"key":"e_1_3_2_1_16_1","volume-title":"Laszlo Lukacs, Ruiqi Guo, Sanjiv Kumar, Balint Miklos, and Ray Kurzweil.","author":"Henderson Matthew","year":"2017","unstructured":"Matthew Henderson, Rami Al-Rfou, Brian Strope, Yun hsuan Sung, Laszlo Lukacs, Ruiqi Guo, Sanjiv Kumar, Balint Miklos, and Ray Kurzweil. 2017. Efficient Natural Language Response Suggestion for Smart Reply. showeprint1705.00652"},{"key":"e_1_3_2_1_17_1","unstructured":"Sebastian Hofst\u00e4tter Sophia Althammer Michael Schr\u00f6der Mete Sertkan and Allan Hanbury. 2021. Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation. showeprint2010.02666"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-21300-6_12"},{"key":"e_1_3_2_1_19_1","first-page":"21102","article-title":"Controlled retrieval-augmented context evaluation for long-form RAG","author":"Ju Jia-Huei","year":"2025","unstructured":"Jia-Huei Ju, Suzan Verberne, Maarten de Rijke, and Andrew Yates. 2025. Controlled retrieval-augmented context evaluation for long-form RAG. In Findings of EMNLP. 21102-21121.","journal-title":"Findings of EMNLP."},{"key":"e_1_3_2_1_20_1","first-page":"6769","article-title":"Dense Passage Retrieval for Open-Domain Question Answering","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering. In Proc. of EMNLP. 6769-6781.","journal-title":"Proc. of EMNLP."},{"key":"e_1_3_2_1_21_1","first-page":"452","article-title":"Natural Questions: A Benchmark for Question Answering Research","volume":"7","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural Questions: A Benchmark for Question Answering Research. Trans. of the ACL, Vol. 7 (2019), 452-466.","journal-title":"Trans. of the ACL"},{"key":"e_1_3_2_1_22_1","first-page":"17606","article-title":"Shifting from ranking to set selection for retrieval augmented generation","author":"Lee Dahyun","year":"2025","unstructured":"Dahyun Lee, Yongrae Jo, Haeju Park, and Moontae Lee. 2025. Shifting from ranking to set selection for retrieval augmented generation. In Proc. of ACL. 17606-17619.","journal-title":"Proc. of ACL."},{"key":"e_1_3_2_1_23_1","first-page":"6086","article-title":"Latent retrieval for weakly supervised open domain question answering","author":"Lee Kenton","year":"2019","unstructured":"Kenton Lee, Ming-Wei Chang, and Kristina Toutanova. 2019. Latent retrieval for weakly supervised open domain question answering. In Proc. of ACL. 6086-6096.","journal-title":"Proc. of ACL."},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. of NIPS.","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, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. Proc. of NIPS."},{"key":"e_1_3_2_1_25_1","unstructured":"Zhicong Li Jiahao Wang Zhishu Jiang Hangyu Mao Zhongxia Chen Jiazhen Du Yuanxing Zhang Fuzheng Zhang Di Zhang and Yong Liu. 2024. DMQR-RAG: Diverse Multi-Query Rewriting for RAG. showeprintarXiv:2411.13154"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.423"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730135"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657846"},{"key":"e_1_3_2_1_29_1","unstructured":"MetaAI. 2024. The Llama 3 herd of models. showeprint2407.21783"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.560"},{"key":"e_1_3_2_1_31_1","volume-title":"Andriy Mulyar, and Brandon Duderstadt.","author":"Nussbaum Zach","year":"2025","unstructured":"Zach Nussbaum, John Xavier Morris, Andriy Mulyar, and Brandon Duderstadt. 2025. Nomic Embed: Training a Reproducible Long Context Text Embedder. TMLR."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Arnold Overwijk Chenyan Xiong Xiao Liu Cameron VandenBerg and Jamie Callan. 2022. Clueweb22: 10 billion web documents with visual and semantic information. showeprint2211.15848","DOI":"10.1145\/3477495.3536321"},{"key":"e_1_3_2_1_33_1","first-page":"5835","article-title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","author":"Qu Yingqi","year":"2021","unstructured":"Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2021. RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering. In Proc. of NAACL-HLT. 5835-5847.","journal-title":"Proc. of NAACL-HLT."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730275"},{"key":"e_1_3_2_1_35_1","first-page":"13468","article-title":"Beyond Factual Accuracy","author":"Samarinas Chris","year":"2025","unstructured":"Chris Samarinas, Alexander Krubner, Alireza Salemi, Youngwoo Kim, and Hamed Zamani. 2025. Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation. In Findings of ACL. 13468-13482.","journal-title":"In Findings of ACL."},{"key":"e_1_3_2_1_36_1","first-page":"136","article-title":"EXAM: How to evaluate retrieve-and-generate systems for users who do not (yet) know what they want","author":"Sander David P","year":"2021","unstructured":"David P Sander and Laura Dietz. 2021. EXAM: How to evaluate retrieve-and-generate systems for users who do not (yet) know what they want. DESIRES, 136-146.","journal-title":"DESIRES"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.566"},{"key":"e_1_3_2_1_38_1","first-page":"6806","article-title":"ProxyQA: An alternative framework for evaluating long-form text generation with large language models","author":"Tan Haochen","year":"2024","unstructured":"Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, and Linqi Song. 2024. ProxyQA: An alternative framework for evaluating long-form text generation with large language models. In Proc. of ACL. 6806-6827.","journal-title":"Proc. of ACL."},{"key":"e_1_3_2_1_39_1","volume-title":"Proc. of NeurIPS.","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Proc. of NeurIPS."},{"key":"e_1_3_2_1_40_1","first-page":"10014","article-title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","author":"Trivedi Harsh","year":"2023","unstructured":"Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. In Proc. of ACL. 10014-10037.","journal-title":"Proc. of ACL."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073483.1073520"},{"key":"e_1_3_2_1_42_1","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. showeprint2502.09017"},{"key":"e_1_3_2_1_43_1","first-page":"2526","article-title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","author":"Warner Benjamin","year":"2025","unstructured":"Benjamin Warner, Antoine Chaffin, Benjamin Clavi\u00e9, Orion Weller, Oskar Hallstr\u00f6m, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, Tom Aarsen, Griffin Thomas Adams, Jeremy Howard, and Iacopo Poli. 2025. Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference. In Proc. of ACL. 2526-2547.","journal-title":"Proc. of ACL."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026516825764"},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. of ICLR.","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval. In Proc. of ICLR."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0335"},{"key":"e_1_3_2_1_47_1","first-page":"247","article-title":"Learning Discriminative Projections for Text Similarity Measures","author":"Yih Wen-Tau","year":"2011","unstructured":"Wen-Tau Yih, Kristina Toutanova, John C Platt, and Christopher Meek. 2011. Learning Discriminative Projections for Text Similarity Measures. In Proc. of CoNLL. 247-256.","journal-title":"Proc. of CoNLL."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615050"},{"key":"e_1_3_2_1_49_1","unstructured":"Yanzhao Zhang Mingxin Li Dingkun Long Xin Zhang Huan Lin Baosong Yang Pengjun Xie An Yang Dayiheng Liu Junyang Lin Fei Huang and Jingren Zhou. 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. showeprint2506.05176"},{"key":"e_1_3_2_1_50_1","unstructured":"Yunfei Zhong Jun Yang Yixing Fan Jiafeng Guo Lixin Su Maarten de Rijke Ruqing Zhang Dawei Yin and Xueqi Cheng. 2025. Reasoning-enhanced query understanding through Decomposition and Interpretation. showeprint2509.06544"}],"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":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:07:01Z","timestamp":1784135221000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809752"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":50,"alternative-id":["10.1145\/3805712.3809752","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809752","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"}}]}}