{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:46:04Z","timestamp":1783737964112,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755674","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"4942-4951","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2685-0031","authenticated-orcid":false,"given":"Ziyan","family":"Liu","sequence":"first","affiliation":[{"name":"East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7048-1386","authenticated-orcid":false,"given":"Junwen","family":"Li","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3121-6292","authenticated-orcid":false,"given":"Kaiwen","family":"Li","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3546-8338","authenticated-orcid":false,"given":"Tong","family":"Ruan","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4843-1953","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5802-6012","authenticated-orcid":false,"given":"Xinyan","family":"He","sequence":"additional","affiliation":[{"name":"Meituan, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9515-7947","authenticated-orcid":false,"given":"Zongyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7044-1341","authenticated-orcid":false,"given":"Xuezhi","family":"Cao","sequence":"additional","affiliation":[{"name":"Meituan, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1687-2227","authenticated-orcid":false,"given":"Jingping","family":"Liu","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45439-5_31"},{"key":"e_1_3_2_1_2_1","volume-title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs. arXiv preprint arXiv:2305.08844","author":"Aky\u00fcrek Afra Feyza","year":"2023","unstructured":"Afra Feyza Aky\u00fcrek, Ekin Aky\u00fcrek, Aman Madaan, Ashwin Kalyan, Peter Clark, Derry Wijaya, and Niket Tandon. 2023. RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs. arXiv preprint arXiv:2305.08844 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.177"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25534"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Zhuo Chen Yichi Zhang Yin Fang Yuxia Geng Lingbing Guo Xiang Chen Qian Li Wen Zhang Jiaoyan Chen Yushan Zhu et al. 2024. Knowledge graphs meet multi-modal learning: A comprehensive survey. arXiv preprint arXiv:2402.05391 (2024).","DOI":"10.2139\/ssrn.5044404"},{"key":"e_1_3_2_1_6_1","volume-title":"Autoregressive entity retrieval. arXiv preprint arXiv:2010.00904","author":"Cao Nicola De","year":"2020","unstructured":"Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2020. Autoregressive entity retrieval. arXiv preprint arXiv:2010.00904 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3407190"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.230"},{"key":"e_1_3_2_1_9_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5627"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475400"},{"key":"e_1_3_2_1_12_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. Minneapolis, Minnesota."},{"key":"e_1_3_2_1_14_1","volume-title":"Improving candidate retrieval with entity profile generation for wikidata entity linking. arXiv preprint arXiv:2202.13404","author":"Lai Tuan Manh","year":"2022","unstructured":"Tuan Manh Lai, Heng Ji, and ChengXiang Zhai. 2022. Improving candidate retrieval with entity profile generation for wikidata entity linking. arXiv preprint arXiv:2202.13404 (2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"Deep learning. nature","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature, Vol. 521, 7553 (2015), 436-444."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29828"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679793"},{"key":"e_1_3_2_1_18_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, Vol. 364 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Entity-based knowledge conflicts in question answering. arXiv preprint arXiv:2109.05052","author":"Longpre Shayne","year":"2021","unstructured":"Shayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris DuBois, and Sameer Singh. 2021. Entity-based knowledge conflicts in question answering. arXiv preprint arXiv:2109.05052 (2021)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599439"},{"key":"e_1_3_2_1_21_1","volume-title":"Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651","author":"Madaan Aman","year":"2023","unstructured":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al., 2023. Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Caiming Xiong, Yingbo Zhou, and Semih Yavuz.","author":"Meng Rui","year":"2024","unstructured":"Rui Meng, Ye Liu, Shafiq Rayhan Joty, Caiming Xiong, Yingbo Zhou, and Semih Yavuz. 2024. Sfrembedding-mistral: enhance text retrieval with transfer learning. Salesforce AI Research Blog, Vol. 3 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Yee Whye Teh, and Tom Rainforth","author":"Miao Ning","year":"2023","unstructured":"Ning Miao, Yee Whye Teh, and Tom Rainforth. 2023. Selfcheck: Using llms to zero-shot check their own step-by-step reasoning. arXiv preprint arXiv:2308.00436 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1186"},{"key":"e_1_3_2_1_25_1","volume-title":"Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. arXiv preprint arXiv:2308.03188","author":"Pan Liangming","year":"2023","unstructured":"Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. 2023. Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. arXiv preprint arXiv:2308.03188 (2023)."},{"key":"e_1_3_2_1_26_1","unstructured":"Baolin Peng Michel Galley Pengcheng He Hao Cheng Yujia Xie Yu Hu Qiuyuan Huang Lars Liden Zhou Yu Weizhu Chen et al. 2023. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:2302.12813 (2023)."},{"key":"e_1_3_2_1_27_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_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"e_1_3_2_1_29_1","first-page":"2556","article-title":"Entity linking meets deep learning: Techniques and solutions","volume":"35","author":"Shen Wei","year":"2021","unstructured":"Wei Shen, Yuhan Li, Yinan Liu, Jiawei Han, Jianyong Wang, and Xiaojie Yuan. 2021. Entity linking meets deep learning: Techniques and solutions. IEEE Transactions on Knowledge and Data Engineering, Vol. 35, 3 (2021), 2556-2578.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2327028"},{"key":"e_1_3_2_1_31_1","first-page":"7654","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING","author":"Shi Senbao","year":"2024","unstructured":"Senbao Shi, Zhenran Xu, Baotian Hu, and Min Zhang. 2024. Generative Multimodal Entity Linking. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 7654-7665."},{"key":"e_1_3_2_1_32_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik R Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505601"},{"key":"e_1_3_2_1_34_1","volume-title":"DWE: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking. arXiv preprint arXiv:2404.04818","author":"Song Shezheng","year":"2024","unstructured":"Shezheng Song, Shasha Li, Shan Zhao, Xiaopeng Li, Chengyu Wang, Jie Yu, Jun Ma, Tianwei Yan, Bin Ji, and Xiaoguang Mao. 2024a. DWE: Dual-Way Matching Enhanced Framework for Multimodal Entity Linking. arXiv preprint arXiv:2404.04818 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29867"},{"key":"e_1_3_2_1_36_1","volume-title":"Cold fusion: Training seq2seq models together with language models. arXiv preprint arXiv:1708.06426","author":"Sriram Anuroop","year":"2017","unstructured":"Anuroop Sriram, Heewoo Jun, Sanjeev Satheesh, and Adam Coates. 2017. Cold fusion: Training seq2seq models together with language models. arXiv preprint arXiv:1708.06426 (2017)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2020.100159"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531867"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.328"},{"key":"e_1_3_2_1_40_1","volume-title":"Generating sequences by learning to self-correct. arXiv preprint arXiv:2211.00053","author":"Welleck Sean","year":"2022","unstructured":"Sean Welleck, Ximing Lu, Peter West, Faeze Brahman, Tianxiao Shen, Daniel Khashabi, and Yejin Choi. 2022. Generating sequences by learning to self-correct. arXiv preprint arXiv:2211.00053 (2022)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.519"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612575"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17189-5_19"},{"key":"e_1_3_2_1_44_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_45_1","volume-title":"AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes. arXiv preprint arXiv:2305.14725","author":"Yao Barry Menglong","year":"2023","unstructured":"Barry Menglong Yao, Yu Chen, Qifan Wang, Sijia Wang, Minqian Liu, Zhiyang Xu, Licheng Yu, and Lifu Huang. 2023. AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes. arXiv preprint arXiv:2305.14725 (2023)."},{"key":"e_1_3_2_1_46_1","volume-title":"Optimizing bi-encoder for named entity recognition via contrastive learning. arXiv preprint arXiv:2208.14565","author":"Zhang Sheng","year":"2022","unstructured":"Sheng Zhang, Hao Cheng, Jianfeng Gao, and Hoifung Poon. 2022. Optimizing bi-encoder for named entity recognition via contrastive learning. arXiv preprint arXiv:2208.14565 (2022)."},{"key":"e_1_3_2_1_47_1","volume-title":"Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking. arXiv preprint arXiv:2406.01934","author":"Zhang Zefeng","year":"2024","unstructured":"Zefeng Zhang, Jiawei Sheng, Chuang Zhang, Yunzhi Liang, Wenyuan Zhang, Siqi Wang, and Tingwen Liu. 2024. Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking. arXiv preprint arXiv:2406.01934 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:03:29Z","timestamp":1765343009000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755674"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":47,"alternative-id":["10.1145\/3746027.3755674","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755674","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}