{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:44Z","timestamp":1784138924489,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":62,"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":"the National Natural Science Foundation of China","award":["62302486"],"award-info":[{"award-number":["62302486"]}]},{"name":"the Innovation Project of ICT CAS","award":["E361140"],"award-info":[{"award-number":["E361140"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809532","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"223-233","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention Grounded Enhancement for Visual Document Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5015-5252","authenticated-orcid":false,"given":"Wanqing","family":"Cui","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1556-8198","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7148-411X","authenticated-orcid":false,"given":"Yazhi","family":"Guo","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7762-6986","authenticated-orcid":false,"given":"Yibo","family":"Hu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3796-2310","authenticated-orcid":false,"given":"Meiguang","family":"Jin","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8589-1006","authenticated-orcid":false,"given":"Junfeng","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-4999","authenticated-orcid":false,"given":"Keping","family":"Bi","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Marah Abdin Sam Ade Jacobs Ammar Ahmad Awan Jyoti Aneja Ahmed Awadallah Hany Hassan Awadalla Nguyen Bach Amit Bahree Arash Bakhtiari Harkirat Singh Behl Alon Benhaim Misha Bilenko Johan Bjorck S\u00e9bastien Bubeck Martin Cai Caio C'esar Teodoro Mendes Weizhu Chen Vishrav Chaudhary Parul Chopra Allison Del Giorno Gustavo de Rosa Matthew Dixon Ronen Eldan Dan Iter Abhishek Goswami Suriya Gunasekar Emman Haider Junheng Hao Russell J. Hewett Jamie Huynh Mojan Javaheripi Xin Jin Piero Kauffmann Nikos Karampatziakis Dongwoo Kim Young Jin Kim Mahoud Khademi Lev Kurilenko James R. Lee Yin Tat Lee Yuanzhi Li Chen Liang Weishung Liu Eric Lin Zeqi Lin Piyush Madan Arindam Mitra Hardik Modi Anh Nguyen Brandon Norick Barun Patra Daniel Perez-Becker Thomas Portet Reid Pryzant Heyang Qin Marko Radmilac Liliang Ren Corby Rosset Sambudha Roy Olli Saarikivi Amin Saied Adil Salim Michael Santacroce Shital Shah Ning Shang Hiteshi Sharma Xianmin Song Olatunji Ruwase Praneetha Vaddamanu Xin Wang Rachel Ward Guanhua Wang Philipp Andre Witte Michael Wyatt Can Xu Jiahang Xu Sonali Yadav Fan Yang Ziyi Yang Donghan Yu Cheng-Yuan Zhang Cyril Zhang Jianwen Zhang Li Lyna Zhang Yi Zhang Yunan Zhang Xiren Zhou and Yifan Yang. 2024. Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone. ArXiv Vol. abs\/2404.14219 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01351"},{"key":"e_1_3_2_1_3_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025a. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_4_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang Humen Zhong Yuanzhi Zhu Mingkun Yang Zhaohai Li Jianqiang Wan Pengfei Wang Wei Ding Zheren Fu Yiheng Xu Jiabo Ye Xi Zhang Tianbao Xie Zesen Cheng Hang Zhang Zhibo Yang Haiyang Xu and Junyang Lin. 2025b. Qwen2.5-VL Technical Report. arXiv:2502.13923 [cs.CV] https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"e_1_3_2_1_5_1","volume-title":"Alexander Kolesnikov, Xiao Wang, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Emanuele Bugliarello, et al.","author":"Beyer Lucas","year":"2024","unstructured":"Lucas Beyer, Andreas Steiner, Andr\u00e9 Susano Pinto, Alexander Kolesnikov, Xiao Wang, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Emanuele Bugliarello, et al., 2024. Paligemma: A versatile 3b vlm for transfer. arXiv preprint arXiv:2407.07726 (2024)."},{"key":"e_1_3_2_1_6_1","unstructured":"Ioana Bica Anastasija Ili\u0107 Matthias Bauer Goker Erdogan Matko Bo\u0161njak Christos Kaplanis Alexey A Gritsenko Matthias Minderer Charles Blundell Razvan Pascanu et al. 2024. Improving fine-grained understanding in image-text pre-training. arXiv preprint arXiv:2401.09865 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02570"},{"key":"e_1_3_2_1_8_1","volume-title":"M3docrag: Multi-modal retrieval is what you need for multi-page multi-document understanding. arXiv preprint arXiv:2411.04952","author":"Cho Jaemin","year":"2024","unstructured":"Jaemin Cho, Debanjan Mahata, Ozan Irsoy, Yujie He, and Mohit Bansal. 2024. M3docrag: Multi-modal retrieval is what you need for multi-page multi-document understanding. arXiv preprint arXiv:2411.04952 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation. arXiv preprint arXiv:2505.21549","author":"Csizmadia Daniel","year":"2025","unstructured":"Daniel Csizmadia, Andrei Codreanu, Victor Sim, Vighnesh Prabhu, Michael Lu, Kevin Zhu, Sean O'Brien, and Vasu Sharma. 2025. Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation. arXiv preprint arXiv:2505.21549 (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"Vision transformers need registers. arXiv preprint arXiv:2309.16588","author":"Darcet Timoth\u00e9e","year":"2023","unstructured":"Timoth\u00e9e Darcet, Maxime Oquab, Julien Mairal, and Piotr Bojanowski. 2023. Vision transformers need registers. arXiv preprint arXiv:2309.16588 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01038"},{"key":"e_1_3_2_1_12_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Faysse Manuel","year":"2024","unstructured":"Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, C\u00e9line Hudelot, and Pierre Colombo. 2024. Colpali: Efficient document retrieval with vision language models. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_14_1","volume-title":"Distilling knowledge from reader to retriever for question answering. arXiv preprint arXiv:2012.04584","author":"Izacard Gautier","year":"2020","unstructured":"Gautier Izacard and Edouard Grave. 2020. Distilling knowledge from reader to retriever for question answering. arXiv preprint arXiv:2012.04584 (2020)."},{"key":"e_1_3_2_1_15_1","volume-title":"Vlm2vec: Training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160","author":"Jiang Ziyan","year":"2024","unstructured":"Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, and Wenhu Chen. 2024. Vlm2vec: Training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.63317\/496bh35o3ybj"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0875"},{"key":"e_1_3_2_1_18_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering.. In EMNLP (1). 6769-6781."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_20_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 18661-18673."},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"Multimodal arxiv: A dataset for improving scientific comprehension of large vision-language models. arXiv preprint arXiv:2403.00231","author":"Li Lei","year":"2024","unstructured":"Lei Li, Yuqi Wang, Runxin Xu, Peiyi Wang, Xiachong Feng, Lingpeng Kong, and Qi Liu. 2024a. Multimodal arxiv: A dataset for improving scientific comprehension of large vision-language models. arXiv preprint arXiv:2403.00231 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Intermediate distillation: Data-efficient distillation from black-box llms for information retrieval. arXiv preprint arXiv:2406.12169","author":"Li Zizhong","year":"2024","unstructured":"Zizhong Li, Haopeng Zhang, and Jiawei Zhang. 2024b. Intermediate distillation: Data-efficient distillation from black-box llms for information retrieval. arXiv preprint arXiv:2406.12169 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.repl4nlp-1.17"},{"key":"e_1_3_2_1_25_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024. LLaVA-NeXT: Improved reasoning OCR and world knowledge. https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"e_1_3_2_1_26_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023b. Visual Instruction Tuning."},{"key":"e_1_3_2_1_27_1","volume-title":"Mmhqa-icl: Multimodal in-context learning for hybrid question answering over text, tables and images. arXiv preprint arXiv:2309.04790","author":"Liu Weihao","year":"2023","unstructured":"Weihao Liu, Fangyu Lei, Tongxu Luo, Jiahe Lei, Shizhu He, Jun Zhao, and Kang Liu. 2023a. Mmhqa-icl: Multimodal in-context learning for hybrid question answering over text, tables and images. arXiv preprint arXiv:2309.04790 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412747"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.626"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3257193"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.373"},{"key":"e_1_3_2_1_32_1","unstructured":"Quentin Mac\u00e9 Ant\u00f3nio Loison and Manuel Faysse. 2025. ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval. arXiv:2505.17166 [cs.IR] https:\/\/arxiv.org\/abs\/2505.17166"},{"key":"e_1_3_2_1_33_1","volume-title":"Infographicvqa. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 1697-1706","author":"Mathew Minesh","year":"2022","unstructured":"Minesh Mathew, Viraj Bagal, Rub\u00e8n Tito, Dimosthenis Karatzas, Ernest Valveny, and CV Jawahar. 2022. Infographicvqa. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 1697-1706."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_35_1","volume-title":"Rizwan Ahmed Khan, and Mueen Uddin","author":"Memon Jamshed","year":"2020","unstructured":"Jamshed Memon, Maira Sami, Rizwan Ahmed Khan, and Mueen Uddin. 2020. Handwritten optical character recognition (OCR): A comprehensive systematic literature review (SLR). IEEE access, Vol. 8 (2020), 142642-142668."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"e_1_3_2_1_37_1","unstructured":"pdfminer. 2014.pdfminer.six. https:\/\/github.com\/pdfminer\/pdfminer.six."},{"key":"e_1_3_2_1_38_1","unstructured":"pymupdf. 2012. PyMuPDF. https:\/\/github.com\/pymupdf\/PyMuPDF."},{"key":"e_1_3_2_1_39_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3236837"},{"key":"e_1_3_2_1_41_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_43_1","unstructured":"Bharat Bhusan Sau Soumya Roy Vinay P Namboodiri and Raghu Sesha Iyengar. 2021. Deep Knowledge Distillation using Trainable Dense Attention.. In BMVC. 72."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_37"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"e_1_3_2_1_48_1","unstructured":"Nomic Team. 2025. Nomic Embed Multimodal: Interleaved Text Image and Screenshots for Visual Document Retrieval. https:\/\/nomic.ai\/blog\/posts\/nomic-embed-multimodal"},{"key":"e_1_3_2_1_49_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_50_1","volume-title":"Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis. arXiv preprint arXiv:2505.10541","author":"Wang Pengfei","year":"2025","unstructured":"Pengfei Wang, Guohai Xu, Weinong Wang, Junjie Yang, Jie Lou, and Yunhua Xue. 2025. Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis. arXiv preprint arXiv:2505.10541 (2025)."},{"key":"e_1_3_2_1_51_1","volume-title":"European Conference on Computer Vision. Springer, 387-404","author":"Wei Cong","year":"2024","unstructured":"Cong Wei, Yang Chen, Haonan Chen, Hexiang Hu, Ge Zhang, Jie Fu, Alan Ritter, and Wenhu Chen. 2024. Uniir: Training and benchmarking universal multimodal information retrievers. In European Conference on Computer Vision. Springer, 387-404."},{"key":"e_1_3_2_1_52_1","volume-title":"FG-CLIP: Fine-Grained Visual and Textual Alignment. arXiv preprint arXiv:2505.05071","author":"Xie Chunyu","year":"2025","unstructured":"Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Gengshen Zhang, Dawei Leng, and Yuhui Yin. 2025. FG-CLIP: Fine-Grained Visual and Textual Alignment. arXiv preprint arXiv:2505.05071 (2025)."},{"key":"e_1_3_2_1_53_1","unstructured":"Mengyao Xu Gabriel Moreira Ronay Ak Radek Osmulski Yauhen Babakhin Zhiding Yu Benedikt Schifferer and Even Oldridge. 2025. Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model. arXiv:2507.05513 [cs.CV] https:\/\/arxiv.org\/abs\/2507.05513"},{"key":"e_1_3_2_1_54_1","volume-title":"Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783","author":"Yao Lewei","year":"2021","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2021. Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)."},{"key":"e_1_3_2_1_55_1","volume-title":"Retrieval-augmented multimodal language modeling. arXiv preprint arXiv:2211.12561","author":"Yasunaga Michihiro","year":"2022","unstructured":"Michihiro Yasunaga, Armen Aghajanyan, Weijia Shi, Rich James, Jure Leskovec, Percy Liang, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2022. Retrieval-augmented multimodal language modeling. arXiv preprint arXiv:2211.12561 (2022)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.292"},{"key":"e_1_3_2_1_57_1","volume-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928","author":"Zagoruyko Sergey","year":"2016","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2016. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv preprint arXiv:1612.03928 (2016)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_59_1","volume-title":"Mllms know where to look: Training-free perception of small visual details with multimodal llms. arXiv preprint arXiv:2502.17422","author":"Zhang Jiarui","year":"2025","unstructured":"Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara, and Filip Ilievski. 2025. Mllms know where to look: Training-free perception of small visual details with multimodal llms. arXiv preprint arXiv:2502.17422 (2025)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29947"},{"key":"e_1_3_2_1_61_1","volume-title":"TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance. arXiv preprint arXiv:2105.07624","author":"Zhu Fengbin","year":"2021","unstructured":"Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, and Tat-Seng Chua. 2021. TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance. arXiv preprint arXiv:2105.07624 (2021)."},{"key":"e_1_3_2_1_62_1","volume-title":"Promptreps: Prompting large language models to generate dense and sparse representations for zero-shot document retrieval. arXiv preprint arXiv:2404.18424","author":"Zhuang Shengyao","year":"2024","unstructured":"Shengyao Zhuang, Xueguang Ma, Bevan Koopman, Jimmy Lin, and Guido Zuccon. 2024. Promptreps: Prompting large language models to generate dense and sparse representations for zero-shot document retrieval. arXiv preprint arXiv:2404.18424 (2024)."}],"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":"2026-07-15T17:28:13Z","timestamp":1784136493000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":62,"alternative-id":["10.1145\/3805712.3809532","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809532","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"}}]}}