{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:38:14Z","timestamp":1775839094240,"version":"3.50.1"},"reference-count":105,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2021ZD0111601"],"award-info":[{"award-number":["2021ZD0111601"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["623B2099"],"award-info":[{"award-number":["623B2099"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325605"],"award-info":[{"award-number":["62325605"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011374"],"award-info":[{"award-number":["2023A1515011374"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou Science and Technology Program","award":["2024A04J6365"],"award-info":[{"award-number":["2024A04J6365"]}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["23-SIS-SMU-028"],"award-info":[{"award-number":["23-SIS-SMU-028"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["23-SIS-SMU-070"],"award-info":[{"award-number":["23-SIS-SMU-070"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3539433","type":"journal-article","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:41:58Z","timestamp":1738867318000},"page":"3830-3846","source":"Crossref","is-referenced-by-count":10,"title":["A Causality-Aware Paradigm for Evaluating Creativity of Multimodal Large Language Models"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2135-1104","authenticated-orcid":false,"given":"Zhongzhan","family":"Huang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}]},{"given":"Shanshan","family":"Zhong","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3400-8943","authenticated-orcid":false,"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}]},{"given":"Shanghua","family":"Gao","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}]},{"given":"Marinka","family":"Zitnik","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, and Guangdong Key Laboratory of Big Data Analysis and Processing, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01258"},{"key":"ref2","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref3","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref4","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"ref5","article-title":"Language models are greedy reasoners: A systematic formal analysis of chain-of-thought","author":"Saparov","year":"2022"},{"key":"ref6","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref8","first-page":"59662","article-title":"What can large language models do in chemistry? a comprehensive benchmark on eight tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-short.11"},{"key":"ref10","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref12","article-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"ref13","article-title":"A survey on benchmarks of multimodal large language models","author":"Li","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref15","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref16","article-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2022"},{"key":"ref17","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kojima"},{"key":"ref18","article-title":"Tree of thoughts: Deliberate problem solving with large language models, May 2023","author":"Yao","year":"2023"},{"key":"ref19","article-title":"Large language model guided tree-of-thought","author":"Long","year":"2023"},{"key":"ref20","first-page":"20227","article-title":"Leap-of-thought: Teaching pre-trained models to systematically reason over implicit knowledge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Talmor"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/502168a"},{"issue":"6515","key":"ref22","first-page":"572","article-title":"Mental leaps: Analogy in creative thought","volume":"373","author":"Holyoak","year":"1995","journal-title":"Nature"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5840\/philtoday198125130"},{"issue":"3","key":"ref24","first-page":"75","article-title":"A review of mental leaps: Analogy in creative thought","volume":"16","author":"Hofstadter","year":"1995","journal-title":"AI Mag."},{"key":"ref25","volume-title":"Mental Leaps: Analogy in Creative Thought","author":"Holyoak","year":"1996"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/10400419409534509"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1017\/S0048577299961619"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1111\/caim.12078"},{"key":"ref29","volume-title":"Thinking, Fast and Slow","author":"Kahneman","year":"2011"},{"key":"ref30","article-title":"Glossary of owarai terms","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.131"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.885"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21430"},{"key":"ref34","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023"},{"key":"ref35","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref36","article-title":"Weak-eval-strong: Evaluating and eliciting lateral thinking of LLMs with situation puzzles","author":"Chen","year":"2024"},{"key":"ref37","article-title":"Lateval: An interactive LLMs evaluation benchmark with incomplete information from lateral thinking puzzles","author":"Huang","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1080\/0031383940380201"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1080\/10400419309534498"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/0031383790230302"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/BF02213373"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1037\/h0048850"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref44","article-title":"Minigpt-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref45","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.858"},{"key":"ref47","article-title":"Unleashing the creative mind: Language model as hierarchical policy for improved exploration on challenging problem solving","author":"Ling","year":"2023"},{"key":"ref48","article-title":"Brainstorm, then select: A generative language model improves its creativity score","volume-title":"Proc. AAAI-23 Workshop Creative AI Across Modalities","author":"Summers-Stay"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-05543-x"},{"key":"ref50","article-title":"Stiffness-aware neural network for learning hamiltonian systems","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-42194-y"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-demos.29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.460"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519729"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2006.22"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.657"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783388"},{"key":"ref58","first-page":"81","article-title":"Learning to evaluate humor in memes based on the incongruity theory","volume-title":"Proc. 2nd Workshop When Creative AI Meets Conversational AI","author":"Tanaka"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3551876.3554802"},{"key":"ref60","first-page":"29","article-title":"A survey on approaches to computational humor generation","volume-title":"Proc. 4th Joint SIGHUM Workshop Comput. Linguistics Cultural Heritage, Social Sci., Humanities Literature","author":"Amin"},{"key":"ref61","article-title":"Let\u2019s be humorous: Knowledge enhanced humor generation","author":"Zhang","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.28"},{"key":"ref63","first-page":"1888","article-title":"Does AI have a sense of humor? CLEF 2023 JOKER tasks 1, 2 and 3: Using BLOOM, GPT, Simplet5, and more for pun detection, location, interpretation and translation","volume-title":"Proc. Work. Notes CLEF","author":"Popova"},{"key":"ref64","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110840","article-title":"Mhadig: A multilingual humor-aided multiparty dialogue generation in multimodal conversational setting","volume":"278","author":"Chauhan","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645553"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref67","first-page":"70757","article-title":"Towards revealing the mystery behind chain of thought: A theoretical perspective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.20"},{"key":"ref69","first-page":"5168","article-title":"DDCoT: Duty-distinct chain-of-thought prompting for multimodal reasoning in language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.41"},{"key":"ref72","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1835449.1835560"},{"key":"ref75","volume-title":"The Leader\u2019s Guide to Lateral Thinking Skills: Powerful Problem-Solving Techniques to Ignite Your Team\u2019s Potential","author":"Sloane","year":"2003"},{"key":"ref76","article-title":"Lateral thinking: Creativity step by step","author":"De Bono","year":"1970"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1428-6_1557"},{"key":"ref78","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref79","article-title":"LORA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref80","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01879"},{"key":"ref83","article-title":"Model dementia: Generated data makes models forget","author":"Shumailov","year":"2023"},{"key":"ref84","article-title":"Exploration of masked and causal language modelling for text generation","author":"Micheletti","year":"2024"},{"key":"ref85","article-title":"tinybenchmarks: Evaluating LLMs with fewer examples","author":"Polo","year":"2024"},{"key":"ref86","article-title":"Metabench\u2013a sparse benchmark to measure general ability in large language models","author":"Kipnis","year":"2024"},{"key":"ref87","article-title":"Mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref89","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref90","first-page":"24185","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Chen"},{"key":"ref91","article-title":"MiniCPM-V: A GPT-4V Level MLLM on your phone","author":"Yao","year":"2024"},{"key":"ref92","article-title":"Yi: Open foundation models by 01. AI","author":"Young","year":"2024"},{"key":"ref93","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref94","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref95","article-title":"Otter: A multi-modal model with in-context instruction tuning","author":"Li","year":"2023"},{"key":"ref96","article-title":"Baichuan 2: Open large-scale language models","year":"2023"},{"key":"ref97","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref99","article-title":"Gpteval: A survey on assessments of chatgpt and GPT-4","author":"Mao","year":"2023"},{"key":"ref100","article-title":"Mllm-bench, evaluating multi-modal LLMs using GPT-4V","author":"Ge","year":"2023"},{"key":"ref101","first-page":"46595","article-title":"Judging LLM-as-a-judge with mt-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref102","article-title":"A measure of similarity in textual data using spearman\u2019s rank correlation coefficient","author":"Arsov","year":"2019"},{"key":"ref103","article-title":"Investigating the catastrophic forgetting in multimodal large language models","author":"Zhai","year":"2023"},{"key":"ref104","article-title":"Quantifying creativity in art networks","author":"Elgammal","year":"2015"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijer.2016.12.004"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10876763.pdf?arnumber=10876763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:13:50Z","timestamp":1744305230000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10876763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":105,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3539433","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}