{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:33:43Z","timestamp":1743143623054,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794423"},{"type":"electronic","value":"9789819794430"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-9443-0_26","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:31:03Z","timestamp":1730392263000},"page":"300-311","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explore the\u00a0Textual Perception Ability on\u00a0the\u00a0Images for\u00a0Multimodal Large Language Models"],"prefix":"10.1007","author":[{"given":"Jiayi","family":"Kuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiarui","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"26_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"doi-asserted-by":"crossref","unstructured":"Cha, J., Kang, W., Mun, J., Roh, B.: Honeybee: locality-enhanced projector for multimodal llm. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13817\u201313827 (2024)","key":"26_CR2","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"26_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-020-1122-3","volume":"20","author":"N Chen","year":"2020","unstructured":"Chen, N., Su, X., Liu, T., Hao, Q., Wei, M.: A benchmark dataset and case study for chinese medical question intent classification. BMC Med. Inform. Decis. Mak. 20, 1\u20137 (2020)","journal-title":"BMC Med. Inform. Decis. Mak."},{"unstructured":"Chen, Z., et al.: Octavius: Mitigating task interference in mllms via lora-moe. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, 7-11 May 2024 (2024)","key":"26_CR4"},{"issue":"8","key":"26_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3554727","volume":"55","author":"C Dong","year":"2022","unstructured":"Dong, C., et al.: A survey of natural language generation. ACM Comput. Surv. 55(8), 1\u201338 (2022)","journal-title":"ACM Comput. Surv."},{"key":"26_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2022.100055","volume":"3","author":"JM Gayed","year":"2022","unstructured":"Gayed, J.M., Carlon, M.K.J., Oriola, A.M., Cross, J.S.: Exploring an ai-based writing assistant\u2019s impact on English language learners. Comput. Educ. Artifi. Intell. 3, 100055 (2022)","journal-title":"Comput. Educ. Artifi. Intell."},{"doi-asserted-by":"crossref","unstructured":"Hu, W., Xu, Y., Li, Y., Li, W., Chen, Z., Tu, Z.: Bliva: a simple multimodal llm for better handling of text-rich visual questions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 2256\u20132264 (2024)","key":"26_CR7","DOI":"10.1609\/aaai.v38i3.27999"},{"doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: A frustratingly easy plug-and-play detection-and-reasoning module for chinese spelling check. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, 6-10 December 2023, pp. 11514\u201311525. Association for Computational Linguistics (2023)","key":"26_CR8","DOI":"10.18653\/v1\/2023.findings-emnlp.771"},{"doi-asserted-by":"crossref","unstructured":"Imran, M., Almusharraf, N.: Analyzing the role of chatgpt as a writing assistant at higher education level: a systematic review of the literature. Contemporary Educ. Technol. 15(4), ep464 (2023)","key":"26_CR9","DOI":"10.30935\/cedtech\/13605"},{"doi-asserted-by":"crossref","unstructured":"Islam, R., Moushi, O.M.: Gpt-4o: The cutting-edge advancement in multimodal llm. Authorea Preprints (2024)","key":"26_CR10","DOI":"10.36227\/techrxiv.171986596.65533294\/v1"},{"doi-asserted-by":"crossref","unstructured":"Ji, T., Yan, H., Qiu, X.: Spellbert: a lightweight pretrained model for Chinese spelling check. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3544\u20133551 (2021)","key":"26_CR11","DOI":"10.18653\/v1\/2021.emnlp-main.287"},{"unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)","key":"26_CR12"},{"unstructured":"Li, Y., et al.: On the (in)effectiveness of large language models for chinese text correction. CoRR abs\/ arXiv: 2307.09007 (2023)","key":"26_CR13"},{"unstructured":"Li, Y., et al.: Rethinking the roles of large language models in Chinese grammatical error correction. CoRR abs\/ arxiv: 2402.11420 (2024)","key":"26_CR14"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Towards real-world writing assistance: a Chinese character checking benchmark with faked and misspelled characters. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8656\u20138668. Association for Computational Linguistics, Bangkok, Thailand (Aug 2024). https:\/\/aclanthology.org\/2024.acl-long.469","key":"26_CR15","DOI":"10.18653\/v1\/2024.acl-long.469"},{"doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: The past mistake is the future wisdom: error-driven contrastive probability optimization for Chinese spell checking. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) Findings of the Association for Computational Linguistics: ACL 2022, Dublin, Ireland, 22-27 May 2022, pp. 3202\u20133213. Association for Computational Linguistics (2022)","key":"26_CR16","DOI":"10.18653\/v1\/2022.findings-acl.252"},{"unstructured":"Li, Y., et al.: When llms meet cunning questions: a fallacy understanding benchmark for large language models. CoRR abs\/ arXiv: 2402.11100 (2024)","key":"26_CR17"},{"issue":"2","key":"26_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1967293.1967297","volume":"10","author":"CL Liu","year":"2011","unstructured":"Liu, C.L., Lai, M.H., Tien, K.W., Chuang, Y.H., Wu, S.H., Lee, C.Y.: Visually and phonologically similar characters in incorrect Chinese words: analyses, identification, and applications. ACM Trans. Asian Lang. Inform. Process. (TALIP) 10(2), 1\u201339 (2011)","journal-title":"ACM Trans. Asian Lang. Inform. Process. (TALIP)"},{"issue":"7","key":"26_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100520","volume":"3","author":"R Liu","year":"2022","unstructured":"Liu, R., Li, Y., Tao, L., Liang, D., Zheng, H.: Are we ready for a new paradigm shift? a survey on visual deep MLP. Patterns 3(7), 100520 (2022)","journal-title":"Patterns"},{"doi-asserted-by":"crossref","unstructured":"Luo, H., Deng, Y., Shen, Y., Ng, S.K., Chua, T.S.: Chain-of-exemplar: enhancing distractor generation for multimodal educational question generation. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7978\u20137993 (2024)","key":"26_CR20","DOI":"10.18653\/v1\/2024.acl-long.432"},{"doi-asserted-by":"crossref","unstructured":"Luo, H., Shen, Y., Deng, Y.: Unifying text, tables, and images for multimodal question answering. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, 6-10 December 2023, pp. 9355\u20139367. Association for Computational Linguistics (2023)","key":"26_CR21","DOI":"10.18653\/v1\/2023.findings-emnlp.626"},{"doi-asserted-by":"crossref","unstructured":"Ma, S., et al.: Linguistic rules-based corpus generation for native chinese grammatical error correction. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2022, Abu Dhabi, United Arab Emirates, 7-11 December 2022, pp. 576\u2013589. Association for Computational Linguistics (2022)","key":"26_CR22","DOI":"10.18653\/v1\/2022.findings-emnlp.40"},{"unstructured":"Qin, L., et al.: Multilingual large language model: A survey of resources, taxonomy and frontiers. CoRR abs\/ arXiv: 2404.04925 (2024)","key":"26_CR23"},{"unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)","key":"26_CR24"},{"issue":"8","key":"26_CR25","doi-asserted-by":"publisher","first-page":"5051","DOI":"10.1109\/TNNLS.2021.3123751","volume":"34","author":"Y Shen","year":"2021","unstructured":"Shen, Y., Yang, M., Li, Y., Wang, D., Zheng, H., Chen, D.: Knowledge-based reasoning network for relation detection. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 5051\u20135063 (2021)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"doi-asserted-by":"crossref","unstructured":"Tseng, Y.H., Lee, L.H., Chang, L.P., Chen, H.H.: Introduction to sighan 2015 bake-off for chinese spelling check. In: Proceedings of the Eighth SIGHAN Workshop on Chinese Language Processing, pp. 32\u201337 (2015)","key":"26_CR26","DOI":"10.18653\/v1\/W15-3106"},{"doi-asserted-by":"crossref","unstructured":"Wang, D., Song, Y., Li, J., Han, J., Zhang, H.: A hybrid approach to automatic corpus generation for Chinese spelling check. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2517\u20132527 (2018)","key":"26_CR27","DOI":"10.18653\/v1\/D18-1273"},{"doi-asserted-by":"crossref","unstructured":"Wang, X., Zhao, R., Dai, H., Li, P.: An empirical investigation of domain adaptation ability for chinese spelling check models. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 9996\u201310000. IEEE (2024)","key":"26_CR28","DOI":"10.1109\/ICASSP48485.2024.10448189"},{"unstructured":"Wu, S.H., Chen, Y.Z., Yang, P.C., Ku, T., Liu, C.L.: Reducing the false alarm rate of chinese character error detection and correction. In: CIPS-SIGHAN Joint Conference on Chinese Language Processing (2010)","key":"26_CR29"},{"unstructured":"Wu, S.H., Liu, C.L., Lee, L.H.: Chinese spelling check evaluation at sighan bake-off 2013. In: Proceedings of the Seventh SIGHAN Workshop on Chinese Language Processing, pp. 35\u201342 (2013)","key":"26_CR30"},{"unstructured":"Yang, Z.,et al.: The dawn of lmms: Preliminary explorations with gpt-4v (ision), 9(1). arXiv preprint arXiv:2309.17421 (2023)","key":"26_CR31"},{"unstructured":"Ye, J., Li, Y., Ma, S., Xie, R., Wu, W., Zheng, H.: Focus is what you need for chinese grammatical error correction. CoRR abs\/ arXiv: 2210.12692 (2022)","key":"26_CR32"},{"doi-asserted-by":"crossref","unstructured":"Ye, J., Li, Y., Zhou, Q., Li, Y., Ma, S., Zheng, H., Shen, Y.: CLEME: debiasing multi-reference evaluation for grammatical error correction. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, 6-10 December 2023, pp. 6174\u20136189. Association for Computational Linguistics (2023)","key":"26_CR33","DOI":"10.18653\/v1\/2023.emnlp-main.378"},{"doi-asserted-by":"crossref","unstructured":"Yu, L.C., Lee, L.H., Tseng, Y.H., Chen, H.H.: Overview of sighan 2014 bake-off for chinese spelling check. In: Proceedings of The Third CIPS-SIGHAN Joint Conference on Chinese Language Processing, pp. 126\u2013132 (2014)","key":"26_CR34","DOI":"10.3115\/v1\/W14-6820"},{"doi-asserted-by":"crossref","unstructured":"Zhan, J., et\u00a0al.: Anygpt: Unified multimodal llm with discrete sequence modeling. arXiv preprint arXiv:2402.12226 (2024)","key":"26_CR35","DOI":"10.18653\/v1\/2024.acl-long.521"},{"doi-asserted-by":"crossref","unstructured":"Zhang, S., Huang, H., Liu, J., Li, H.: Spelling error correction with soft-masked bert. arXiv preprint arXiv:2005.07421 (2020)","key":"26_CR36","DOI":"10.18653\/v1\/2020.acl-main.82"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9443-0_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:35:55Z","timestamp":1730392555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9443-0_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794423","9789819794430"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9443-0_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}