{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:10:06Z","timestamp":1755889806093,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.62402105, No. 62272098, No.U24B20152"],"award-info":[{"award-number":["No.62402105, No. 62272098, No.U24B20152"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730081","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:18:36Z","timestamp":1752455916000},"page":"1000-1010","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Seeing Beyond Hallucinations: LLM-based Compositional Information Extraction for Multimodal Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0147-858X","authenticated-orcid":false,"given":"Xinwei","family":"Li","sequence":"first","affiliation":[{"name":"Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3511-5559","authenticated-orcid":false,"given":"Li","family":"Lin","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3609-2205","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1215-8919","authenticated-orcid":false,"given":"Hanqian","family":"Wu","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591875"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arxiv: 2308.12966 [cs.CV] https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00253"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591758"},{"volume-title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model. In The Eleventh International Conference on Learning Representations.","author":"Chen Xi","key":"e_1_3_2_1_7_1","unstructured":"Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, et al. [n.,d.]. PaLI: A Jointly-Scaled Multilingual Language-Image Model. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_8_1","volume-title":"ACM SIGIR Forum","volume":"57","author":"Chua Tat-Seng","year":"2024","unstructured":"Tat-Seng Chua. 2024. Towards Generative Search and Recommendation: A keynote at RecSys 2023. In ACM SIGIR Forum, Vol. 57. ACM New York, NY, USA, 1--14."},{"key":"e_1_3_2_1_9_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arxiv: 2305.06500 [cs.CV] https:\/\/arxiv.org\/abs\/2305.06500"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"e_1_3_2_1_12_1","volume-title":"Visual perturbation-aware collaborative learning for overcoming the language prior problem. arXiv preprint arXiv:2207.11850","author":"Han Yudong","year":"2022","unstructured":"Yudong Han, Liqiang Nie, Jianhua Yin, Jianlong Wu, and Yan Yan. 2022. Visual perturbation-aware collaborative learning for overcoming the language prior problem. arXiv preprint arXiv:2207.11850 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Does Prompt Formatting Have Any Impact on LLM Performance? arXiv preprint arXiv:2411.10541","author":"He Jia","year":"2024","unstructured":"Jia He, Mukund Rungta, David Koleczek, Arshdeep Sekhon, Franklin X Wang, and Sadid Hasan. 2024. Does Prompt Formatting Have Any Impact on LLM Performance? arXiv preprint arXiv:2411.10541 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.870"},{"key":"e_1_3_2_1_15_1","unstructured":"Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings convolutional neural networks and incremental parsing. (2017). To appear."},{"key":"e_1_3_2_1_16_1","volume-title":"Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality. Advances in neural information processing systems","author":"Hsieh Cheng-Yu","year":"2024","unstructured":"Cheng-Yu Hsieh, Jieyu Zhang, Zixian Ma, Aniruddha Kembhavi, and Ranjay Krishna. 2024. Sugarcrepe: Fixing hackable benchmarks for vision-language compositionality. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591790"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_1_20_1","volume-title":"What's'' up'' with vision-language models? Investigating their struggle with spatial reasoning. arXiv preprint arXiv:2310.19785","author":"Kamath Amita","year":"2023","unstructured":"Amita Kamath, Jack Hessel, and Kai-Wei Chang. 2023. What's'' up'' with vision-language models? Investigating their struggle with spatial reasoning. arXiv preprint arXiv:2310.19785 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00257"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"e_1_3_2_1_25_1","volume-title":"Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326","author":"Li Bo","year":"2024","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, et al. 2024a. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)."},{"key":"e_1_3_2_1_26_1","volume-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895","author":"Li Feng","year":"2024","unstructured":"Feng Li, Renrui Zhang, Hao Zhang, Yuanhan Zhang, Bo Li, Wei Li, Zejun Ma, and Chunyuan Li. 2024b. Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023c. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_29_1","volume-title":"2023 d. A large-scale dataset towards multi-modal multilingual instruction tuning. arXiv preprint arXiv:2306.04387","author":"Li Lei","year":"2023","unstructured":"Lei Li, Yuwei Yin, Shicheng Li, Liang Chen, Peiyi Wang, Shuhuai Ren, Mukai Li, Yazheng Yang, Jingjing Xu, Xu Sun, et al. 2023 d. A large-scale dataset towards multi-modal multilingual instruction tuning. arXiv preprint arXiv:2306.04387, Vol. 3 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.687"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. 740--755."},{"key":"e_1_3_2_1_34_1","volume-title":"Aligning large multi-modal model with robust instruction tuning. arXiv preprint arXiv:2306.14565","author":"Liu Fuxiao","year":"2023","unstructured":"Fuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, and Lijuan Wang. 2023b. Aligning large multi-modal model with robust instruction tuning. arXiv preprint arXiv:2306.14565 (2023)."},{"key":"e_1_3_2_1_35_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li Bo Li Yuanhan Zhang Sheng Shen and Yong Jae Lee. 2024b. 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_36_1","first-page":"34892","article-title":"Visual Instruction Tuning","volume":"36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023a. Visual Instruction Tuning. In Advances in Neural Information Processing Systems, Vol. 36. 34892--34916.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1016"},{"key":"e_1_3_2_1_40_1","volume-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255","author":"Lu Pan","year":"2023","unstructured":"Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. 2023. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"e_1_3_2_1_43_1","volume-title":"Contrastive decoding improves reasoning in large language models. arXiv preprint arXiv:2309.09117","author":"O'Brien Sean","year":"2023","unstructured":"Sean O'Brien and Mike Lewis. 2023. Contrastive decoding improves reasoning in large language models. arXiv preprint arXiv:2309.09117 (2023)."},{"key":"e_1_3_2_1_44_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report."},{"key":"e_1_3_2_1_45_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_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"e_1_3_2_1_47_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, Vol. 35 (2022), 36479--36494."},{"key":"e_1_3_2_1_48_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25278--25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_50_1","unstructured":"Zhiqing Sun Sheng Shen Shengcao Cao Haotian Liu Chunyuan Li Yikang Shen Chuang Gan Liang-Yan Gui Yu-Xiong Wang Yiming Yang et al. 2023. Aligning large multimodal models with factually augmented rlhf. arXiv preprint arXiv:2309.14525 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_12"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657905"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01761"},{"key":"e_1_3_2_1_55_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657727"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14167-2"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657740"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591879"},{"key":"e_1_3_2_1_60_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yarom Michal","year":"2024","unstructured":"Michal Yarom, Yonatan Bitton, Soravit Changpinyo, Roee Aharoni, Jonathan Herzig, Oran Lang, Eran Ofek, and Idan Szpektor. 2024. What you see is what you read? improving text-image alignment evaluation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_61_1","unstructured":"Jiahui Yu Zirui Wang Vijay Vasudevan Legg Yeung Mojtaba Seyedhosseini and Yonghui Wu. [n. d.]. CoCa: Contrastive Captioners are Image-Text Foundation Models. Transactions on Machine Learning Research ( [n. d.])."},{"key":"e_1_3_2_1_62_1","volume-title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities. In International Conference on Machine Learning. PMLR, 57730--57754","author":"Yu Weihao","year":"2024","unstructured":"Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2024. MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities. In International Conference on Machine Learning. PMLR, 57730--57754."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"e_1_3_2_1_64_1","volume-title":"Less is more: Mitigating multimodal hallucination from an eos decision perspective. arXiv preprint arXiv:2402.14545","author":"Yue Zihao","year":"2024","unstructured":"Zihao Yue, Liang Zhang, and Qin Jin. 2024b. Less is more: Mitigating multimodal hallucination from an eos decision perspective. arXiv preprint arXiv:2402.14545 (2024)."},{"key":"e_1_3_2_1_65_1","volume-title":"When and why vision-language models behave like bags-of-words, and what to do about it? arXiv preprint arXiv:2210.01936","author":"Yuksekgonul Mert","year":"2022","unstructured":"Mert Yuksekgonul, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, and James Zou. 2022. When and why vision-language models behave like bags-of-words, and what to do about it? arXiv preprint arXiv:2210.01936 (2022)."},{"key":"e_1_3_2_1_66_1","volume-title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning. PMLR, 25994--26009","author":"Zeng Yan","year":"2022","unstructured":"Yan Zeng, Xinsong Zhang, and Hang Li. 2022. Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts. In International Conference on Machine Learning. PMLR, 25994--26009."},{"key":"e_1_3_2_1_67_1","volume-title":"Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923","author":"Zhang Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, and Alex Smola. 2023. Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923 (2023)."},{"key":"e_1_3_2_1_68_1","volume-title":"Vl-checklist: Evaluating pre-trained vision-language models with objects, attributes and relations. arXiv preprint arXiv:2207.00221","author":"Zhao Tiancheng","year":"2022","unstructured":"Tiancheng Zhao, Tianqi Zhang, Mingwei Zhu, Haozhan Shen, Kyusong Lee, Xiaopeng Lu, and Jianwei Yin. 2022. Vl-checklist: Evaluating pre-trained vision-language models with objects, attributes and relations. arXiv preprint arXiv:2207.00221 (2022)."},{"key":"e_1_3_2_1_69_1","first-page":"5168","article-title":"Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","volume":"36","author":"Zheng Ge","year":"2023","unstructured":"Ge Zheng, Bin Yang, Jiajin Tang, Hong-Yu Zhou, and Sibei Yang. 2023. Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 5168--5191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_70_1","volume-title":"Proceedings of the 22nd Chinese National Conference on Computational Linguistics. 600--610","author":"Zhibo Ren","year":"2023","unstructured":"Ren Zhibo, Wang Huizhen, Zhu Muhua, Wang Yichao, Xiao Tong, and Zhu Jingbo. 2023. Overcoming language priors with counterfactual inference for visual question answering. In Proceedings of the 22nd Chinese National Conference on Computational Linguistics. 600--610."},{"volume-title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following.","author":"Zhou Yiyang","key":"e_1_3_2_1_71_1","unstructured":"Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, and Huaxiu Yao. [n.d.]. Analyzing and Mitigating Object Hallucination in Large Vision-Language Models. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:32:16Z","timestamp":1755887536000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":71,"alternative-id":["10.1145\/3726302.3730081","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730081","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}