{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T01:44:08Z","timestamp":1772675048731,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong RGC ECS","award":["22200722"],"award-info":[{"award-number":["22200722"]}]},{"name":"Code Generation Techniques in Compound AI Systems and Applications through Huawei gift fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tkde.2025.3637552","type":"journal-article","created":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T19:05:31Z","timestamp":1764183931000},"page":"1040-1053","source":"Crossref","is-referenced-by-count":1,"title":["ExplainHM++: Explainable Harmful Meme Detection With Retrieval-Augmented Debate Between Large Multimodal Models"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4111-8334","authenticated-orcid":false,"given":"Hongzhan","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2028-2407","authenticated-orcid":false,"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7464-8331","authenticated-orcid":false,"given":"Jing","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8122-5943","authenticated-orcid":false,"given":"Yang","family":"Deng","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[{"name":"Jilin University, Changchun, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruichao","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9429.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/781"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"ref4","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kiela"},{"key":"ref5","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref6","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/665"},{"key":"ref12","first-page":"344","article-title":"The hateful memes challenge: Competition report","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Competition Demonstration Track","author":"Kiela"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.611"},{"key":"ref14","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref15","volume-title":"Dialectical Thinking","author":"Basseches","year":"1984"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-99468-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645381"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.semeval-1.74"},{"key":"ref20","article-title":"Minicpm-V: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024"},{"key":"ref21","article-title":"Supervised multimodal bitransformers for classifying images and text","author":"Kiela","year":"2019"},{"key":"ref22","first-page":"32","article-title":"Multimodal meme dataset (multioff) for identifying offensive content in image and text","volume-title":"Proc. 2nd Workshop Trolling Aggression Cyberbullying","author":"Suryawanshi"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2998805"},{"key":"ref24","article-title":"Detecting hate speech in multi-modal memes","author":"Das","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","article-title":"A multimodal framework for the detection of hateful memes","author":"Lippe","year":"2020"},{"key":"ref28","article-title":"Vilio: State-of-the-art visio-linguistic models applied to hateful memes","author":"Muennighoff","year":"2020"},{"key":"ref29","article-title":"Detecting hate speech in memes using multimodal deep learning approaches: Prize-winning solution to hateful memes challenge","author":"Velioglu","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512260"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455994"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3501247.3531557"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.291"},{"key":"ref34","article-title":"Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution","author":"Zhu","year":"2020"},{"key":"ref35","article-title":"Detecting hateful memes using a multimodal deep ensemble","author":"Sandulescu","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587427"},{"key":"ref37","article-title":"AI safety via debate","author":"Irving","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"ref39","first-page":"11733","article-title":"Improving factuality and reasoning in language models through multiagent debate","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref40","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lewis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"ref42","article-title":"Improving language models by retrieving from trillions of tokens","author":"Borgeaud","year":"2022"},{"key":"ref43","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3729239"},{"key":"ref47","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref48","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref49","article-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30214"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"ref52","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS 2014 Workshop Deep Learn. Representation Learn.","author":"Hinton","year":"2015"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.151"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref56","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478328"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref60","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00373"},{"key":"ref62","article-title":"GPT-4 technical report","year":"2023"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11329113\/11269674.pdf?arnumber=11269674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T18:33:13Z","timestamp":1767810793000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11269674\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":62,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3637552","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}