{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:22:52Z","timestamp":1783225372153,"version":"3.54.6"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576073"],"award-info":[{"award-number":["62576073"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["25AYY004"],"award-info":[{"award-number":["25AYY004"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113369","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:09:15Z","timestamp":1772582955000},"page":"113369","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Multimodal metaphor understanding and generation in MLLMs: A dataset and reasoning framework"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1655-2291","authenticated-orcid":false,"given":"Senqi","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7683-5560","authenticated-orcid":false,"given":"Dongyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8444-1419","authenticated-orcid":false,"given":"Zihang","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8251-6964","authenticated-orcid":false,"given":"Haojia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4936-5758","authenticated-orcid":false,"given":"Guiru","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5281-3111","authenticated-orcid":false,"given":"Qi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6362-7084","authenticated-orcid":false,"given":"Wanqiu","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7258-1059","authenticated-orcid":false,"given":"Zeqi","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4208-1566","authenticated-orcid":false,"given":"Wei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9362-6718","authenticated-orcid":false,"given":"Mingshuo","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0872-7688","authenticated-orcid":false,"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113369_bib0001","series-title":"Metaphor in Educational Discourse","author":"Cameron","year":"2003"},{"key":"10.1016\/j.patcog.2026.113369_bib0002","series-title":"Metaphors We Live By","author":"Lakoff","year":"1980"},{"issue":"3","key":"10.1016\/j.patcog.2026.113369_bib0003","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1080\/10926488.2022.2153336","article-title":"Code red for humanity: multimodal metaphor and metonymy in noncommercial advertisements on environmental awareness and activism","volume":"38","author":"Hidalgo-Downing","year":"2023","journal-title":"Metaphor Symb."},{"key":"10.1016\/j.patcog.2026.113369_bib0004","first-page":"379","article-title":"Non-verbal and multimodal metaphor in a cognitivist framework: agendas for research","volume":"1","author":"Forceville","year":"2006","journal-title":"Appl. Cognit. Linguist."},{"key":"10.1016\/j.patcog.2026.113369_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112752","article-title":"A multi-expert framework for enhancing multimodal large language models in industrial anomaly detection","volume":"172","author":"Chen","year":"2026","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2026.113369_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111670","article-title":"MLLM as video narrator: mitigating modality imbalance in video moment retrieval","volume":"166","author":"Cai","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113369_bib0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111783","article-title":"Exp-VQA: fine-grained facial expression analysis via visual question answering","volume":"168","author":"Yuan","year":"2025","journal-title":"Pattern Recognit."},{"issue":"12","key":"10.1016\/j.patcog.2026.113369_bib0008","doi-asserted-by":"crossref","DOI":"10.1145\/3773989","article-title":"Towards multimodal metaphor understanding: a chinese dataset and model for metaphor mapping identification","volume":"24","author":"Zhang","year":"2025","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"issue":"1","key":"10.1016\/j.patcog.2026.113369_bib0009","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s40747-024-01684-w","article-title":"Metaphor recognition based on cross-modal multi-level information fusion","volume":"11","author":"Yang","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.patcog.2026.113369_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111778","article-title":"What do they \u201cmeme\u201d? A metaphor-aware multi-modal multi-task framework for fine-grained meme understanding","volume":"294","author":"Wang","year":"2024","journal-title":"Knowl. Based Syst."},{"issue":"1","key":"10.1016\/j.patcog.2026.113369_bib0011","doi-asserted-by":"crossref","first-page":"273","DOI":"10.17507\/tpls.1401.32","article-title":"A multimodal metaphor analysis of wechat emoticon from the perspective of visual grammar","volume":"14","author":"Wang","year":"2024","journal-title":"Theory Pract. Language Studies"},{"key":"10.1016\/j.patcog.2026.113369_bib0012","series-title":"Proceedings of the 45th International ACM SIGIR","first-page":"2887","article-title":"MET-Meme: a multimodal meme dataset rich in metaphors","author":"Xu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113369_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23201","article-title":"Metaclue: towards comprehensive visual metaphors research","author":"Akula","year":"2023"},{"key":"10.1016\/j.patcog.2026.113369_bib0014","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"3517","article-title":"Metaphor understanding challenge dataset for LLMs","author":"Tong","year":"2024"},{"key":"10.1016\/j.patcog.2026.113369_bib0015","series-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4437","article-title":"Testing the ability of language models to interpret figurative language","author":"Liu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113369_bib0016","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1162\/tacl_a_00478","article-title":"It\u2019s not rocket science: interpreting figurative language in narratives","volume":"10","author":"Chakrabarty","year":"2022","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.patcog.2026.113369_bib0017","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"7731","article-title":"A theory guided scaffolding instruction framework for LLM-enabled metaphor reasoning","author":"Tian","year":"2024"},{"key":"10.1016\/j.patcog.2026.113369_bib0018","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1018","article-title":"Does GPT-3 grasp metaphors? identifying metaphor mappings with generative language models","author":"Wachowiak","year":"2023"},{"key":"10.1016\/j.patcog.2026.113369_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110399","article-title":"Prompting large language model with context and pre-answer for knowledge-based VQA","volume":"151","author":"Hu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113369_bib0020","series-title":"The Eleventh International Conference on Learning Representations (ICLR 2023)","article-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113369_bib0021","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"2609","article-title":"Plan-and-solve prompting: improving zero-Shot chain-of-thought reasoning by large language models","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113369_bib0022","series-title":"Advances in Neural Information Processing Systems","first-page":"11809","article-title":"Tree of thoughts: deliberate problem solving with large language models","volume":"36","author":"Yao","year":"2023"},{"key":"10.1016\/j.patcog.2026.113369_bib0023","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","article-title":"Multimet: a multimodal dataset for metaphor understanding","author":"Zhang","year":"2021"},{"key":"10.1016\/j.patcog.2026.113369_bib0024","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"688","article-title":"Do androids laugh at electric sheep? humor \u201cUnderstanding\u201d benchmarks from the new yorker caption contest","author":"Hessel","year":"2023"},{"key":"10.1016\/j.patcog.2026.113369_bib0025","series-title":"Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12Th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)","first-page":"373","article-title":"MiQA: a benchmark for inference on metaphorical questions","author":"ComSa","year":"2022"},{"issue":"5","key":"10.1016\/j.patcog.2026.113369_bib0026","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1037\/h0031619","article-title":"Measuring nominal scale agreement among many raters","volume":"76","author":"Fleiss","year":"1971","journal-title":"Psychol. Bull."},{"issue":"10","key":"10.1016\/j.patcog.2026.113369_bib0027","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1016\/j.patcog.2010.08.016","article-title":"Latent visual context learning for web image applications","volume":"44","author":"Zhou","year":"2011","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113369_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112140","article-title":"Efficient greedy optimization method for k-means","volume":"171","author":"Yuan","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113369_bib0029","unstructured":"F. Qi, C. Yang, Z. Liu, Q. Dong, M. Sun, Z. Dong, OpenHowNet: an open sememe-based lexical knowledge base, (2019). arXiv: 1901.09957."},{"key":"10.1016\/j.patcog.2026.113369_bib0030","unstructured":"S. Bai, K. Chen, X. Liu, J. Wang, W. Ge, S. Song, K. Dang, P. Wang, S. Wang, J. Tang, et al., Qwen2.5-VL technical report, (2025). arXiv: 2502.13923."},{"key":"10.1016\/j.patcog.2026.113369_bib0031","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"Rouge: a package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.patcog.2026.113369_bib0032","series-title":"International Conference on Learning Representations","article-title":"BERTScore: evaluating text generation with BERT","author":"Zhang","year":"2020"},{"key":"10.1016\/j.patcog.2026.113369_bib0033","series-title":"International Conference on Representation Learning","first-page":"19426","article-title":"Large language models are not robust multiple choice selectors","volume":"2024","author":"Zheng","year":"2024"},{"issue":"10","key":"10.1016\/j.patcog.2026.113369_bib0034","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1007\/s10462-024-10888-y","article-title":"Large language models (LLMs): survey, technical frameworks, and future challenges","volume":"57","author":"Kumar","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.patcog.2026.113369_bib0035","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"1732","article-title":"Leveraging generative large language models with visual instruction and demonstration retrieval for multimodal sarcasm detection","author":"Tang","year":"2024"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003341?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003341?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:05:14Z","timestamp":1779383114000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326003341"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":35,"alternative-id":["S0031320326003341"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113369","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multimodal metaphor understanding and generation in MLLMs: A dataset and reasoning framework","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113369","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113369"}}