{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:11:40Z","timestamp":1778080300512,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031784552","type":"print"},{"value":"9783031784569","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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\/978-3-031-78456-9_15","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T11:24:42Z","timestamp":1733138682000},"page":"226-241","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A Benchmark and Chain-of-Thought Prompting Strategy for Large Multimodal Models with Multiple Image Inputs"],"prefix":"10.1007","author":[{"given":"Daoan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Junming","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Hanjia","family":"Lyu","sequence":"additional","affiliation":[]},{"given":"Zijian","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Mingkai","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"15_CR1","unstructured":"Awadalla, A., Gao, I., Gardner, J., Hessel, J., Hanafy, Y., Zhu, W., Marathe, K., Bitton, Y., Gadre, S., Sagawa, S., et\u00a0al.: Openflamingo: An open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)"},{"key":"15_CR2","unstructured":"Cui, C., Zhou, Y., Yang, X., Wu, S., Zhang, L., Zou, J., Yao, H.: Holistic analysis of hallucination in gpt-4v (ision): Bias and interference challenges. arXiv preprint arXiv:2311.03287 (2023)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Hu, Y., Ganter, T., Deilamsalehy, H., Dernoncourt, F., Foroosh, H., Liu, F.: Meetingbank: A benchmark dataset for meeting summarization. arXiv preprint arXiv:2305.17529 (2023)","DOI":"10.18653\/v1\/2023.acl-long.906"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Hu, Y., Song, K., Cho, S., Wang, X., Foroosh, H., Liu, F.: Decipherpref: Analyzing influential factors in human preference judgments via gpt-4. arXiv preprint arXiv:2305.14702 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.519"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Hu, Y., Hua, H., Yang, Z., Shi, W., Smith, N.A., Luo, J.: Promptcap: Prompt-guided task-aware image captioning. arXiv preprint arXiv:2211.09699 (2022)","DOI":"10.1109\/ICCV51070.2023.00277"},{"key":"15_CR6","unstructured":"Hua, H., Li, X., Dou, D., Xu, C.Z., Luo, J.: Fine-tuning pre-trained language models with noise stability regularization. arXiv preprint arXiv:2206.05658 (2022)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Hua, H., Shi, J., Kafle, K., Jenni, S., Zhang, D., Collomosse, J., Cohen, S., Luo, J.: Finematch: Aspect-based fine-grained image and text mismatch detection and correction. arXiv preprint arXiv:2404.14715 (2024)","DOI":"10.1007\/978-3-031-72673-6_26"},{"key":"15_CR8","unstructured":"Huang, S., Dong, L., Wang, W., Hao, Y., Singhal, S., Ma, S., Lv, T., Cui, L., Mohammed, O.K., Liu, Q., et\u00a0al.: Language is not all you need: Aligning perception with language models. arXiv preprint arXiv:2302.14045 (2023)"},{"key":"15_CR9","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. Adv. Neural. Inf. Process. Syst. 35, 22199\u201322213 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: Benchmarking multimodal llms with generative comprehension. arXiv preprint arXiv:2307.16125 (2023)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Li, C., Zhang, D., Huang, W., Zhang, J.: Cross contrasting feature perturbation for domain generalization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1327\u20131337 (2023)","DOI":"10.1109\/ICCV51070.2023.00128"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"15_CR13","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Liu, X., Liu, P., He, H.: An empirical analysis on large language models in debate evaluation. arXiv preprint arXiv:2406.00050 (2024)","DOI":"10.18653\/v1\/2024.acl-short.44"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Duan, H., Zhang, Y., Li, B., Zhang, S., Zhao, W., Yuan, Y., Wang, J., He, C., Liu, Z., et\u00a0al.: Mmbench: Is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"15_CR16","unstructured":"Lyu, H., Huang, J., Zhang, D., Yu, Y., Mou, X., Pan, J., Yang, Z., Wei, Z., Luo, J.: Gpt-4v (ision) as a social media analysis engine. arXiv preprint arXiv:2311.07547 (2023)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Mitra, C., Huang, B., Darrell, T., Herzig, R.: Compositional chain-of-thought prompting for large multimodal models. arXiv preprint arXiv:2311.17076 (2023)","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"15_CR18","doi-asserted-by":"publisher","unstructured":"OpenAI: GPT-4 technical report. CoRR abs\/2303.08774 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.08774, https:\/\/doi.org\/10.48550\/arXiv.2303.08774","DOI":"10.48550\/ARXIV.2303.08774"},{"key":"15_CR19","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR20","unstructured":"Suryavardan, S., Mishra, S., Patwa, P., Chakraborty, M., Rani, A., Reganti, A., Chadha, A., Das, A., Sheth, A., Chinnakotla, M., et\u00a0al.: Factify 2: A multimodal fake news and satire news dataset. arXiv preprint arXiv:2304.03897 (2023)"},{"key":"15_CR21","unstructured":"Tang, Y., Zhang, J., Wang, X., Wang, T., Zheng, F.: Llmva-gebc: Large language model with video adapter for generic event boundary captioning. arXiv preprint arXiv:2306.10354 (2023)"},{"key":"15_CR22","unstructured":"Team, G., Anil, R., Borgeaud, S., Wu, Y., Alayrac, J.B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., et\u00a0al.: Gemini: A family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Thrush, T., Jiang, R., Bartolo, M., Singh, A., Williams, A., Kiela, D., Ross, C.: Winoground: Probing vision and language models for visio-linguistic compositionality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"15_CR24","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"15_CR25","unstructured":"Wang, J., Zhou, Y., Xu, G., Shi, P., Zhao, C., Xu, H., Ye, Q., Yan, M., Zhang, J., Zhu, J., et\u00a0al.: Evaluation and analysis of hallucination in large vision-language models. arXiv preprint arXiv:2308.15126 (2023)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Xie, Z., Deng, S., Liu, P., Lou, X., Xu, C., Li, D.: Characterizing anti-vaping posts for effective communication on instagram using multimodal deep learning. Nicotine and Tobacco Research 26(Supplement_1), S43\u2013S48 (2024)","DOI":"10.1093\/ntr\/ntad189"},{"key":"15_CR27","unstructured":"Yin, Z., Wang, J., Cao, J., Shi, Z., Liu, D., Li, M., Huang, X., Wang, Z., Sheng, L., Bai, L., et\u00a0al.: Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"15_CR28","unstructured":"Yu, W., Yang, Z., Li, L., Wang, J., Lin, K., Liu, Z., Wang, X., Wang, L.: Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Yu, Y., Du, D., Zhang, L., Luo, T.: Unbiased multi-modality guidance for image inpainting. In: European Conference on Computer Vision. pp. 668\u2013684. Springer (2022)","DOI":"10.1007\/978-3-031-19787-1_38"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Yue, X., Ni, Y., Zhang, K., Zheng, T., Liu, R., Zhang, G., Stevens, S., Jiang, D., Ren, W., Sun, Y., et\u00a0al.: Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. arXiv preprint arXiv:2311.16502 (2023)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, C., Gao, F., Jia, B., Zhu, Y., Zhu, S.C.: Raven: A dataset for relational and analogical visual reasoning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 5317\u20135327 (2019)","DOI":"10.1109\/CVPR.2019.00546"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, D., Zhang, W., He, B., Zhang, J., Qin, C., Yao, J.: Dnagpt: A generalized pretrained tool for multiple dna sequence analysis tasks. bioRxiv pp. 2023\u201307 (2023)","DOI":"10.1101\/2023.07.11.548628"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, R., Hu, X., Li, B., Huang, S., Deng, H., Qiao, Y., Gao, P., Li, H.: Prompt, generate, then cache: Cascade of foundation models makes strong few-shot learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15211\u201315222 (2023)","DOI":"10.1109\/CVPR52729.2023.01460"},{"key":"15_CR34","unstructured":"Zhao, H., Cai, Z., Si, S., Ma, X., An, K., Chen, L., Liu, Z., Wang, S., Han, W., Chang, B.: Mmicl: Empowering vision-language model with multi-modal in-context learning. arXiv preprint arXiv:2309.07915 (2023)"},{"key":"15_CR35","unstructured":"Zhao, Y., Pang, T., Du, C., Yang, X., Li, C., Cheung, N.M.M., Lin, M.: On evaluating adversarial robustness of large vision-language models. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"15_CR36","unstructured":"Zheng, G., Yang, B., Tang, J., Zhou, H.Y., Yang, S.: Ddcot: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models. arXiv preprint arXiv:2310.16436 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78456-9_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T12:11:04Z","timestamp":1733141464000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78456-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784552","9783031784569"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78456-9_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}