{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T13:00:49Z","timestamp":1743080449113,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620708"},{"type":"electronic","value":"9789819620715"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-2071-5_29","type":"book-chapter","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T15:34:23Z","timestamp":1735745663000},"page":"398-412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating VQA Models\u2019 Consistency in\u00a0the\u00a0Scientific Domain"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7096-111X","authenticated-orcid":false,"given":"Khanh-An C.","family":"Quan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-8715","authenticated-orcid":false,"given":"Camille","family":"Guinaudeau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6995-6447","authenticated-orcid":false,"given":"Shin\u2019ichi","family":"Satoh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,2]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: VQA: visual question answering. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"29_CR2","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"key":"29_CR3","unstructured":"Fu, C., et al.: Mme: a comprehensive evaluation benchmark for multimodal large language models (2024)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Ho, N., Schmid, L., Yun, S.Y.: Large language models are reasoning teachers. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) ACL, pp. 14852\u201314882 (Jul 2023)","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Hsieh, C.Y., et al.: Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) ACL, pp. 8003\u20138017, Jul 2023","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Kafle, K., Price, B., Cohen, S., Kanan, C.: Dvqa: understanding data visualizations via question answering. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5648\u20135656 (2018)","DOI":"10.1109\/CVPR.2018.00592"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV, pp. 235\u2013251. Springer International Publishing (2016)","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Seo, M., Schwenk, D., Choi, J., Farhadi, A., Hajishirzi, H.: Are you smarter than a sixth grader? textbook question answering for multimodal machine comprehension. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5376\u20135384 (2017)","DOI":"10.1109\/CVPR.2017.571"},{"key":"29_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. NeurIPS 35, 22199\u201322213 (2022)","journal-title":"NeurIPS"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Krishnamurthy, J., Tafjord, O., Kembhavi, A.: Semantic parsing to probabilistic programs for situated question answering. In: Su, J., Duh, K., Carreras, X. (eds.) EMNLP, pp. 160\u2013170 (Nov 2016)","DOI":"10.18653\/v1\/D16-1016"},{"key":"29_CR11","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":"29_CR12","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Mmbench: Is your multi-modal model an all-around player? (2024)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"29_CR14","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: NeurIPS (2022)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Magister, L.C., Mallinson, J., Adamek, J., Malmi, E., Severyn, A.: Teaching small language models to reason. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 1773\u20131781. ACL (Jul 2023)","DOI":"10.18653\/v1\/2023.acl-short.151"},{"key":"29_CR16","unstructured":"OpenAI: GPT-4 technical report. CoRR abs\/2303.08774 (2023)"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Sampat, S.K., Yang, Y., Baral, C.: Visuo-linguistic question answering (VLQA) challenge. In: Cohn, T., He, Y., Liu, Y. (eds.) EMNLP, pp. 4606\u20134616, November 2020","DOI":"10.18653\/v1\/2020.findings-emnlp.413"},{"key":"29_CR18","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: T-sciq: teaching multimodal chain-of-thought reasoning via large language model signals for science question answering. AAAI 38, 19162\u201319170 (03 2024)","DOI":"10.1609\/aaai.v38i17.29884"},{"key":"29_CR20","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q.V., Zhou, D., et al.: Chain-of-thought prompting elicits reasoning in large language models. NeurIPS 35, 24824\u201324837 (2022)","journal-title":"NeurIPS"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Xu, P., et al.: Lvlm-ehub: a comprehensive evaluation benchmark for large vision-language models. arXiv preprint arXiv:2306.09265 (2023)","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"29_CR22","unstructured":"Yin, Z., et\u00a0al.: Lamm: language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"29_CR23","unstructured":"Zhang, R., et al.: Llama-adapter: efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"29_CR24","unstructured":"Zhang, Z., Zhang, A., Li, M., Zhao, H., Karypis, G., Smola, A.: Multimodal chain-of-thought reasoning in language models. Transactions on Machine Learning Research (2024)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2071-5_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T16:03:57Z","timestamp":1735747437000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2071-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819620708","9789819620715"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2071-5_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}