{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:11:10Z","timestamp":1777651870783,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819722648","type":"print"},{"value":"9789819722624","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-2262-4_5","type":"book-chapter","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T09:02:31Z","timestamp":1713949351000},"page":"53-64","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["MM-PhyQA: Multimodal Physics Question-Answering with\u00a0Multi-image CoT Prompting"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2479-0342","authenticated-orcid":false,"given":"Avinash","family":"Anand","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9562-7672","authenticated-orcid":false,"given":"Janak","family":"Kapuriya","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2589-8293","authenticated-orcid":false,"given":"Apoorv","family":"Singh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3177-149X","authenticated-orcid":false,"given":"Jay","family":"Saraf","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2914-5509","authenticated-orcid":false,"given":"Naman","family":"Lal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3615-5373","authenticated-orcid":false,"given":"Astha","family":"Verma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1399-8262","authenticated-orcid":false,"given":"Rushali","family":"Gupta","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1028-9373","authenticated-orcid":false,"given":"Rajiv","family":"Shah","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"5_CR1","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"5_CR2","unstructured":"Jiang, A.Q., et al.: Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"5_CR3","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/978-3-031-49601-1_4","volume-title":"International Conference on Big Data Analytics","author":"A Anand","year":"2023","unstructured":"Anand, A., et al.: SciPhyRAG-retrieval augmentation to improve LLMs on physics Q & A. In: Goyal, V., Kumar, N., Bhowmick, S.S., Goyal, P., Goyal, N., Kumar, D. (eds.) BDA 2023. LNCS, vol. 14418, pp. 50\u201363. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-49601-1_4"},{"key":"5_CR4","unstructured":"OpenAI: GPT-4 technical report. ArXiv abs\/2303.08774 (2023). n. pag"},{"key":"5_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1007\/978-3-031-49601-1_6","volume-title":"Big Data and Artificial Intelligence","author":"A Anand","year":"2023","unstructured":"Anand, A., et al.: Context-enhanced language models for generating multi-paper citations. In: Goyal, V., Kumar, N., Bhowmick, S.S., Goyal, P., Goyal, N., Kumar, D. (eds.) BDA 2023. LNCS, vol. 14418, pp. 80\u201394. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-49601-1_6"},{"key":"5_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/978-3-031-49601-1_3","volume-title":"Big Data and Artificial Intelligence","author":"A Anand","year":"2023","unstructured":"Anand, A., et al.: KG-CTG: citation generation through knowledge graph-guided large language models. In: Goyal, V., Kumar, N., Bhowmick, S.S., Goyal, P., Goyal, N., Kumar, D. (eds.) BDA 2023. LNCS, vol. 14418, pp. 37\u201349. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-49601-1_3"},{"key":"5_CR7","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR8","first-page":"2507","volume":"35","author":"P Lu","year":"2022","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. Adv. Neural. Inf. Process. Syst. 35, 2507\u20132521 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR9","unstructured":"Zhang, Z., Zhang, A., Li, M., Zhao, H., Karypis, G., Smola, A.: Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923 (2023)"},{"key":"5_CR10","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Arora, D., Singh, H.G.: Have LLMs advanced enough? A challenging problem solving benchmark for large language models. arXiv preprint arXiv:2305.15074 (2023). pag","DOI":"10.18653\/v1\/2023.emnlp-main.468"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Welbl, J., Liu, N.F., Gardner, M.: Crowdsourcing multiple choice science questions. arXiv preprint arXiv:1707.06209 (2017)","DOI":"10.18653\/v1\/W17-4413"},{"key":"5_CR13","unstructured":"Wang, X., et al.: SciBench: evaluating college-level scientific problem-solving abilities of large language models. ArXiv abs\/2307.10635 (2023). n. pag"},{"key":"5_CR14","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)"},{"key":"5_CR15","unstructured":"Huang, Y., et al.: C-eval: a multi-level multi-discipline Chinese evaluation suite for foundation models. arXiv preprint arXiv:2305.08322 (2023)"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: GeoQA: a geometric question answering benchmark towards multimodal numerical reasoning. arXiv preprint arXiv:2105.14517 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"5_CR17","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/978-981-19-7596-7_14","volume-title":"Knowledge Graph and Semantic Computing: Knowledge Graph Empowers the Digital Economy","author":"N Jin","year":"2022","unstructured":"Jin, N., Siebert, J., Li, D., Chen, Q.: A survey on table question answering: recent advances. In: Sun, M., et al. (eds.) CCKS 2022. CCIS, vol. 1669, pp. 174\u2013186. Springer, Singapore (2022). https:\/\/doi.org\/10.1007\/978-981-19-7596-7_14"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S., Hoque, E.: ChartQA: a benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"5_CR19","unstructured":"Deepak, G., Kumari, S., Ekbal, A., Bhattacharyya, P.: MMQA: a multi-domain multi-lingual question-answering framework for English and Hindi. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)"},{"key":"5_CR20","unstructured":"https:\/\/openai.com\/research\/gpt-4v-system-card"},{"key":"5_CR21","unstructured":"Driess, D., et al.: PaLM-E: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"5_CR22","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"5_CR24","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"5_CR25","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic. arXiv preprint arXiv:2306.15195 (2023)"},{"key":"5_CR26","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. arXiv preprint arXiv:2306.14824 (2023)"},{"key":"5_CR27","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601 (2023)"},{"key":"5_CR28","unstructured":"Besta, M., et al.: Graph of thoughts: solving elaborate problems with large language models. arXiv preprint arXiv:2308.09687 (2023)"},{"key":"5_CR29","unstructured":"https:\/\/chat.openai.com\/"},{"key":"5_CR30","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. CoRR abs\/2106.09685 (2021)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2262-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T23:03:58Z","timestamp":1731798238000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2262-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819722648","9789819722624"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2262-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taipei","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","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":"7 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}