{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:28Z","timestamp":1786120828200,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U25B2064"],"award-info":[{"award-number":["U25B2064"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817680","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"1780-1791","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4618-1140","authenticated-orcid":false,"given":"Ruofan","family":"Hu","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8567-2185","authenticated-orcid":false,"given":"Menghui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5666-8320","authenticated-orcid":false,"given":"Jieming","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3750-2533","authenticated-orcid":false,"given":"Bo","family":"Chen","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5705-7932","authenticated-orcid":false,"given":"Shengyang","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0368-2527","authenticated-orcid":false,"given":"Minjie","family":"Hong","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7297-4536","authenticated-orcid":false,"given":"Xiaoda","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9245-4639","authenticated-orcid":false,"given":"Sashuai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0461-8452","authenticated-orcid":false,"given":"Li","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3564-1628","authenticated-orcid":false,"given":"Tao","family":"Jin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_17"},{"key":"e_1_3_2_1_2_1","unstructured":"Marah Abdin Jyoti Aneja Harkirat Behl S\u00e9bastien Bubeck Ronen Eldan Suriya Gunasekar Michael Harrison Russell J Hewett Mojan Javaheripi Piero Kauffmann et al. 2024. Phi-4 technical report. arXiv preprint arXiv:2412.08905 (2024)."},{"key":"e_1_3_2_1_3_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_1_4_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1080\/02687038.2015.1100709"},{"key":"e_1_3_2_1_6_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_7_1","unstructured":"Antoine Chaffin and Aur\u00e9lien Lac. 2024. MonoQwen: Visual Document Reranking. https:\/\/huggingface.co\/lightonai\/MonoQwen2-VL-v0.1"},{"key":"e_1_3_2_1_8_1","volume-title":"Alexander Toshev, Jonathon Shlens, Ruoming Pang, and Yinfei Yang.","author":"Chen Chen","year":"2023","unstructured":"Chen Chen, Bowen Zhang, Liangliang Cao, Jiguang Shen, Tom Gunter, Albin Madappally Jose, Alexander Toshev, Jonathon Shlens, Ruoming Pang, and Yinfei Yang. 2023b. Stair: Learning sparse text and image representation in grounded tokens. arXiv preprint arXiv:2301.13081 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Walking down the memory maze: Beyond context limit through interactive reading. arXiv preprint arXiv:2310.05029","author":"Chen Howard","year":"2023","unstructured":"Howard Chen, Ramakanth Pasunuru, Jason Weston, and Asli Celikyilmaz. 2023a. Walking down the memory maze: Beyond context limit through interactive reading. arXiv preprint arXiv:2310.05029 (2023)."},{"key":"e_1_3_2_1_10_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_11_1","first-page":"288","volume-title":"International Conference on Learning Representations","volume":"2025","author":"Cheng Xize","year":"2025","unstructured":"Xize Cheng, Ruofan Hu, Xiaoda Yang, Jingyu Lu, Dongjie Fu, Shengpeng Ji, Rongjie Huang, Boyang Zhang, Tao Jin, Zhou Zhao, et al., 2025. Voxdialogue: Can spoken dialogue systems understand information beyond words?. In International Conference on Learning Representations, Vol. 2025. 288-303."},{"key":"e_1_3_2_1_12_1","volume-title":"Chaoqun Liu, Maojia Song, Sharifah Mahani Aljunied, Soujanya Poria, and Lidong Bing.","author":"Chia Yew Ken","year":"2024","unstructured":"Yew Ken Chia, Liying Cheng, Hou Pong Chan, Chaoqun Liu, Maojia Song, Sharifah Mahani Aljunied, Soujanya Poria, and Lidong Bing. 2024. M-longdoc: A benchmark for multimodal super-long document understanding and a retrieval-aware tuning framework. arXiv preprint arXiv:2411.06176 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW69036.2025.00649"},{"key":"e_1_3_2_1_14_1","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multimodality long context and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)."},{"key":"e_1_3_2_1_15_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_16_1","volume-title":"MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering. arXiv preprint arXiv:2404.12720","author":"Ding Yihao","year":"2024","unstructured":"Yihao Ding, Kaixuan Ren, Jiabin Huang, Siwen Luo, and Soyeon Caren Han. 2024. MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering. arXiv preprint arXiv:2404.12720 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Dexun Li, Ruiming Tang, and Yong Liu.","author":"Dong Kuicai","year":"2025","unstructured":"Kuicai Dong, Yujing Chang, Xin Deik Goh, Dexun Li, Ruiming Tang, and Yong Liu. 2025a. MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents. arXiv preprint arXiv:2501.08828 (2025)."},{"key":"e_1_3_2_1_18_1","volume-title":"Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering. arXiv preprint arXiv:2505.16470","author":"Dong Kuicai","year":"2025","unstructured":"Kuicai Dong, Yujing Chang, Shijie Huang, Yasheng Wang, Ruiming Tang, and Yong Liu. 2025b. Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering. arXiv preprint arXiv:2505.16470 (2025)."},{"key":"e_1_3_2_1_19_1","first-page":"2650","article-title":"GTA: Towards generative text-to-audio retrieval via multi-scale tokenizer","author":"Fang Minghui","year":"2025","unstructured":"Minghui Fang, Shengpeng Ji, Jialong Zuo, Xize Cheng, Wenrui Liu, Xiaoda Yang, Ruofan Hu, Jieming Zhu, and Zhou Zhao. 2025. GTA: Towards generative text-to-audio retrieval via multi-scale tokenizer. In Proc. Interspeech. 2650-2654.","journal-title":"Proc. Interspeech."},{"key":"e_1_3_2_1_20_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_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_1_22_1","volume-title":"Isabelle Mohr, Andrei Ungureanu, Sedigheh Eslami, Scott Martens, Bo Wang, Nan Wang, and Han Xiao.","author":"G\u00fcnther Michael","year":"2025","unstructured":"Michael G\u00fcnther, Saba Sturua, Mohammad Kalim Akram, Isabelle Mohr, Andrei Ungureanu, Sedigheh Eslami, Scott Martens, Bo Wang, Nan Wang, and Han Xiao. 2025. jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval. arXiv preprint arXiv:2506.18902 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Generative Reasoning Recommendation via LLMs. arXiv preprint arXiv:2510.20815","author":"Hong Minjie","year":"2025","unstructured":"Minjie Hong, Zetong Zhou, Zirun Guo, Ziang Zhang, Ruofan Hu, Weinan Gan, Jieming Zhu, and Zhou Zhao. 2025. Generative Reasoning Recommendation via LLMs. arXiv preprint arXiv:2510.20815 (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"Tensorized embedding layers for efficient model compression. arXiv preprint arXiv:1901.10787","author":"Hrinchuk Oleksii","year":"2019","unstructured":"Oleksii Hrinchuk, Valentin Khrulkov, Leyla Mirvakhabova, Elena Orlova, and Ivan Oseledets. 2019. Tensorized embedding layers for efficient model compression. arXiv preprint arXiv:1901.10787 (2019)."},{"key":"e_1_3_2_1_25_1","volume-title":"Vela: Scalable embeddings with voice large language models for multimodal retrieval. arXiv preprint arXiv:2506.14445","author":"Hu Ruofan","year":"2025","unstructured":"Ruofan Hu, Yan Xia, Minjie Hong, Jieming Zhu, Bo Chen, Xiaoda Yang, Minghui Fang, and Tao Jin. 2025. Vela: Scalable embeddings with voice large language models for multimodal retrieval. arXiv preprint arXiv:2506.14445 (2025)."},{"key":"e_1_3_2_1_26_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_27_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_28_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_29_1","volume-title":"Meta-task prompting elicits embeddings from large language models. arXiv preprint arXiv:2402.18458","author":"Lei Yibin","year":"2024","unstructured":"Yibin Lei, Di Wu, Tianyi Zhou, Tao Shen, Yu Cao, Chongyang Tao, and Andrew Yates. 2024. Meta-task prompting elicits embeddings from large language models. arXiv preprint arXiv:2402.18458 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"V20, 1","author":"Lesk Michael E","year":"1969","unstructured":"Michael E Lesk. 1969. Word-word associations in document retrieval systems. American documentation, V20, 1 (1969), 27-38."},{"key":"e_1_3_2_1_31_1","unstructured":"Chaofan Li Zheng Liu Shitao Xiao and Yingxia Shao. 2023a. Making Large Language Models A Better Foundation For Dense Retrieval. arXiv:2312.15503 [cs.CL]"},{"key":"e_1_3_2_1_32_1","volume-title":"Mrg-bench: Evaluating and exploring the requirements of context for repository-level code generation. arXiv preprint arXiv:2508.02998","author":"Li Haiyang","year":"2025","unstructured":"Haiyang Li. 2025. Mrg-bench: Evaluating and exploring the requirements of context for repository-level code generation. arXiv preprint arXiv:2508.02998 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"V37","author":"Li Yifan","year":"2024","unstructured":"Yifan Li, Yikai Wang, Yanwei Fu, Dongyu Ru, Zheng Zhang, and Tong He. 2024. Unified lexical representation for interpretable visual-language alignment. Advances in Neural Information Processing Systems, V37 (2024), 1141-1161."},{"key":"e_1_3_2_1_34_1","volume-title":"Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023b. Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Mm-embed: Universal multimodal retrieval with multimodal llms. arXiv preprint arXiv:2411.02571","author":"Lin Sheng-Chieh","year":"2024","unstructured":"Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi, Jimmy Lin, Bryan Catanzaro, and Wei Ping. 2024. Mm-embed: Universal multimodal retrieval with multimodal llms. arXiv preprint arXiv:2411.02571 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"Llm4ranking: An easy-to-use framework of utilizing large language models for document reranking. arXiv preprint arXiv:2504.07439","author":"Liu Qi","year":"2025","unstructured":"Qi Liu, Haozhe Duan, Yiqun Chen, Quanfeng Lu, Weiwei Sun, and Jiaxin Mao. 2025. Llm4ranking: An easy-to-use framework of utilizing large language models for document reranking. arXiv preprint arXiv:2504.07439 (2025)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"e_1_3_2_1_38_1","volume-title":"Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning. arXiv preprint arXiv:2510.26205","author":"Luo Qi","year":"2025","unstructured":"Qi Luo, Xiaonan Li, Tingshuo Fan, Xinchi Chen, and Xipeng Qiu. 2025. Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning. arXiv preprint arXiv:2510.26205 (2025)."},{"key":"e_1_3_2_1_39_1","volume-title":"Unifying multimodal retrieval via document screenshot embedding. arXiv preprint arXiv:2406.11251","author":"Ma Xueguang","year":"2024","unstructured":"Xueguang Ma, Sheng-Chieh Lin, Minghan Li, Wenhu Chen, and Jimmy Lin. 2024a. Unifying multimodal retrieval via document screenshot embedding. arXiv preprint arXiv:2406.11251 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Unifying Multimodal Retrieval via Document Screenshot Embedding. arXiv:2406.11251","author":"Ma Xueguang","year":"2024","unstructured":"Xueguang Ma, Sheng-Chieh Lin, Minghan Li, Wenhu Chen, and Jimmy Lin. 2024b. Unifying Multimodal Retrieval via Document Screenshot Embedding. arXiv:2406.11251 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Mmlongbench-doc: Benchmarking long-context document understanding with visualizations. arXiv preprint arXiv:2407.01523","author":"Ma Yubo","year":"2024","unstructured":"Yubo Ma, Yuhang Zang, Liangyu Chen, Meiqi Chen, Yizhu Jiao, Xinze Li, Xinyuan Lu, Ziyu Liu, Yan Ma, Xiaoyi Dong, et al., 2024c. Mmlongbench-doc: Benchmarking long-context document understanding with visualizations. arXiv preprint arXiv:2407.01523 (2024)."},{"key":"e_1_3_2_1_42_1","volume-title":"ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval. arXiv preprint arXiv:2505.17166","author":"Mac\u00e9 Quentin","year":"2025","unstructured":"Quentin Mac\u00e9, Ant\u00f3nio Loison, and Manuel Faysse. 2025. ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval. arXiv preprint arXiv:2505.17166 (2025)."},{"key":"e_1_3_2_1_43_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_44_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_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_46_1","volume-title":"Multimodal learned sparse retrieval for image suggestion. arXiv preprint arXiv:2402.07736","author":"Nguyen Thong","year":"2024","unstructured":"Thong Nguyen, Mariya Hendriksen, and Andrew Yates. 2024. Multimodal learned sparse retrieval for image suggestion. arXiv preprint arXiv:2402.07736 (2024)."},{"key":"e_1_3_2_1_47_1","volume-title":"Document ranking with a pretrained sequence-to-sequence model. arXiv preprint arXiv:2003.06713","author":"Nogueira Rodrigo","year":"2020","unstructured":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin. 2020. Document ranking with a pretrained sequence-to-sequence model. arXiv preprint arXiv:2003.06713 (2020)."},{"key":"e_1_3_2_1_48_1","first-page":"83","volume-title":"Proceedings of IS","volume":"3","author":"Plisson Jo\u00ebl","year":"2004","unstructured":"Jo\u00ebl Plisson, Nada Lavrac, Dunja Mladenic, et al., 2004. A rule based approach to word lemmatization. In Proceedings of IS, Vol. 3. sn, 83-86."},{"key":"e_1_3_2_1_49_1","first-page":"29","volume-title":"Proceedings of the first instructional conference on machine learning","volume":"242","author":"Juan","unstructured":"Juan Ramos et al., 2003. Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning, Vol. 242. New Jersey, USA, 29-48."},{"key":"e_1_3_2_1_50_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_51_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 V3 4 (2009) 333-389.","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"e_1_3_2_1_53_1","volume-title":"LLMs are Also Effective Embedding Models: An In-depth Overview. arXiv preprint arXiv:2412.12591","author":"Tao Chongyang","year":"2024","unstructured":"Chongyang Tao, Tao Shen, Shen Gao, Junshuo Zhang, Zhen Li, Zhengwei Tao, and Shuai Ma. 2024. LLMs are Also Effective Embedding Models: An In-depth Overview. arXiv preprint arXiv:2412.12591 (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"Geneol: Harnessing the generative power of llms for training-free sentence embeddings. arXiv preprint arXiv:2410.14635","author":"Thirukovalluru Raghuveer","year":"2024","unstructured":"Raghuveer Thirukovalluru and Bhuwan Dhingra. 2024. Geneol: Harnessing the generative power of llms for training-free sentence embeddings. arXiv preprint arXiv:2410.14635 (2024)."},{"key":"e_1_3_2_1_55_1","volume-title":"The information bottleneck method. arXiv preprint physics\/0004057","author":"Tishby Naftali","year":"2000","unstructured":"Naftali Tishby, Fernando C Pereira, and William Bialek. 2000. The information bottleneck method. arXiv preprint physics\/0004057 (2000)."},{"key":"e_1_3_2_1_56_1","volume-title":"V144","author":"Tito Rub\u00e8n","year":"2023","unstructured":"Rub\u00e8n Tito, Dimosthenis Karatzas, and Ernest Valveny. 2023. Hierarchical multimodal transformers for multipage docvqa. Pattern Recognition, V144 (2023), 109834."},{"key":"e_1_3_2_1_57_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"e_1_3_2_1_59_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_60_1","volume-title":"Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672","author":"Wang Liang","year":"2024","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024b. Multilingual e5 text embeddings: A technical report. arXiv preprint arXiv:2402.05672 (2024)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.511"},{"key":"e_1_3_2_1_62_1","volume-title":"Conference on learning theory. PMLR, 25-54","author":"Wang Yining","year":"2013","unstructured":"Yining Wang, Liwei Wang, Yuanzhi Li, Di He, and Tie-Yan Liu. 2013. A theoretical analysis of NDCG type ranking measures. In Conference on learning theory. PMLR, 25-54."},{"key":"e_1_3_2_1_63_1","volume-title":"MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval. arXiv preprint arXiv:2506.12364","author":"Xu Mingjun","year":"2025","unstructured":"Mingjun Xu, Jinhan Dong, Jue Hou, Zehui Wang, Sihang Li, Zhifeng Gao, Renxin Zhong, and Hengxing Cai. 2025. MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval. arXiv preprint arXiv:2506.12364 (2025)."},{"key":"e_1_3_2_1_64_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025b. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_65_1","volume-title":"Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in NLP models. arXiv preprint arXiv:2103.15543","author":"Yang Wenkai","year":"2021","unstructured":"Wenkai Yang, Lei Li, Zhiyuan Zhang, Xuancheng Ren, Xu Sun, and Bin He. 2021. Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in NLP models. arXiv preprint arXiv:2103.15543 (2021)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737062"},{"key":"e_1_3_2_1_67_1","volume-title":"Visrag: Vision-based retrieval-augmented generation on multi-modality documents. arXiv preprint arXiv:2410.10594","author":"Yu Shi","year":"2024","unstructured":"Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, et al., 2024. Visrag: Vision-based retrieval-augmented generation on multi-modality documents. arXiv preprint arXiv:2410.10594 (2024)."},{"key":"e_1_3_2_1_68_1","volume-title":"Multi-view document representation learning for open-domain dense retrieval. arXiv preprint arXiv:2203.08372","author":"Zhang Shunyu","year":"2022","unstructured":"Shunyu Zhang, Yaobo Liang, Ming Gong, Daxin Jiang, and Nan Duan. 2022. Multi-view document representation learning for open-domain dense retrieval. arXiv preprint arXiv:2203.08372 (2022)."},{"key":"e_1_3_2_1_69_1","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track. 1393-1412","author":"Zhang Xin","year":"2024","unstructured":"Xin Zhang, Yanzhao Zhang, Dingkun Long, Wen Xie, Ziqi Dai, Jialong Tang, Huan Lin, Baosong Yang, Pengjun Xie, Fei Huang, et al., 2024. mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track. 1393-1412."},{"key":"e_1_3_2_1_70_1","volume-title":"Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176","author":"Zhang Yanzhao","year":"2025","unstructured":"Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al., 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176 (2025)."},{"key":"e_1_3_2_1_71_1","volume-title":"Zhicheng Dou, Siqi Bao, et al.","author":"Zhou Junjie","year":"2025","unstructured":"Junjie Zhou, Ze Liu, Lei Xiong, Jin-Ge Yao, Yueze Wang, Shitao Xiao, Fenfen Lin, Miguel Hu Chen, Zhicheng Dou, Siqi Bao, et al., 2025. MR-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval. arXiv preprint arXiv:2509.26378 (2025)."},{"key":"e_1_3_2_1_72_1","volume-title":"Visual in-context learning for large vision-language models. arXiv preprint arXiv:2402.11574","author":"Zhou Yucheng","year":"2024","unstructured":"Yucheng Zhou, Xiang Li, Qianning Wang, and Jianbing Shen. 2024. Visual in-context learning for large vision-language models. arXiv preprint arXiv:2402.11574 (2024)."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548422"},{"key":"e_1_3_2_1_74_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)."},{"key":"e_1_3_2_1_75_1","volume-title":"V30, 4","author":"Zhuohao WANG","year":"2021","unstructured":"WANG Zhuohao, WANG Dong, and LI Qing. 2021. Keyword extraction from scientific research projects based on SRP-TF-IDF. Chinese Journal of Electronics, V30, 4 (2021), 652-657."},{"key":"e_1_3_2_1_76_1","volume-title":"Docbench: A benchmark for evaluating llm-based document reading systems. arXiv preprint arXiv:2407.10701","author":"Zou Anni","year":"2024","unstructured":"Anni Zou, Wenhao Yu, Hongming Zhang, Kaixin Ma, Deng Cai, Zhuosheng Zhang, Hai Zhao, and Dong Yu. 2024. Docbench: A benchmark for evaluating llm-based document reading systems. arXiv preprint arXiv:2407.10701 (2024)."}],"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.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:24:20Z","timestamp":1786065860000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":76,"alternative-id":["10.1145\/3770855.3817680","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817680","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}