{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:17:19Z","timestamp":1783315039436,"version":"3.54.6"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Double First-Class Special Program for Security and Protection Engineering at the People\u2019s Public Security University of China","award":["No. 2023SYL08"],"award-info":[{"award-number":["No. 2023SYL08"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02223-y","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T11:47:14Z","timestamp":1776426434000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reducing image bias: collaborative multi-role reasoning with adaptive modality filtering for multimodal stance detection (ChinaMM2025\u2013PaperID:119)"],"prefix":"10.1007","volume":"32","author":[{"given":"Teli","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyue","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"key":"2223_CR1","doi-asserted-by":"crossref","unstructured":"Shah, R.R.: Multimodal analysis of user-generated content in support of social media applications. In: ACM ICMR, pp. 423\u2013426 (2016)","DOI":"10.1145\/2911996.2912032"},{"key":"2223_CR2","doi-asserted-by":"crossref","unstructured":"Wen, H., Hauptmann, A.G.: Zero-shot and few-shot stance detection on varied topics via conditional generation. In: ACL, pp. 1491\u20131499 (2023)","DOI":"10.18653\/v1\/2023.acl-short.127"},{"key":"2223_CR3","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"2223_CR4","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: ICML, pp. 5583\u20135594. PMLR (2021)"},{"key":"2223_CR5","doi-asserted-by":"crossref","unstructured":"Liang, B., Li, A., Zhao, J., Gui, L., Yang, M., Yu, Y., Wong, K.-F., Xu, R.: Multi-modal stance detection: New datasets and model (2024). arXiv preprint arXiv:2402.14298","DOI":"10.18653\/v1\/2024.findings-acl.736"},{"key":"2223_CR6","doi-asserted-by":"crossref","unstructured":"Niu, F., Cheng, Z., Fu, X., Peng, X., Dai, G., Chen, Y., Huang, H., Zhang, B.: Multimodal multi-turn conversation stance detection: A challenge dataset and effective model. In: ACM MM, pp. 3867\u20133876 (2024)","DOI":"10.1145\/3664647.3681416"},{"key":"2223_CR7","doi-asserted-by":"crossref","unstructured":"Mohammad, S., Kiritchenko, S., Sobhani, P., Zhu, X., Cherry, C.: Semeval-2016 task 6: Detecting stance in tweets. In: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 31\u201341 (2016)","DOI":"10.18653\/v1\/S16-1003"},{"key":"2223_CR8","unstructured":"Khiabani, P.J., et al.: Cross-target stance detection: A survey of techniques, datasets, and challenges. Expert Systems with Applications (2025)"},{"key":"2223_CR9","doi-asserted-by":"crossref","unstructured":"Ma, J., Wang, C., Xing, H., Zhao, D., Zhang, Y.: Chain of stance: stance detection with large language model. In:CCF International Conference on Natural Language Processing and Chinese Computing,pp.82-94(2024)","DOI":"10.1007\/978-981-97-9443-0_7"},{"key":"2223_CR10","unstructured":"Keshavarz, M., et al.: Large language models meet stance detection: a survey. arXiv preprint arXiv:2505.08464 (2025)"},{"key":"2223_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, Y., Zhang, J., Xu, H.: LLM-driven knowledge injection advances zero-shot and cross-target stance detection. In: Proceedings of NAACL 2024 (Short Papers), pp. 371\u2013378 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.naacl-short.32 . https:\/\/aclanthology.org\/2024.naacl-short.32\/","DOI":"10.18653\/v1\/2024.naacl-short.32"},{"key":"2223_CR12","doi-asserted-by":"crossref","unstructured":"Dubreuil, A., et al.: Are stereotypes leading LLMs\u2019zero-shot stance detection? In: Proceedings of EMNLP2025, pp.31505-31518 (2025). https:\/\/aclanthology.org\/2025.emnlp-main.1605\/","DOI":"10.18653\/v1\/2025.emnlp-main.1605"},{"key":"2223_CR13","doi-asserted-by":"crossref","unstructured":"Vijayaraghavan, P., Vosoughi, S., Roy, D.: Automatic detection and categorization of election-related tweets. In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 10, pp. 703\u2013706 (2016)","DOI":"10.1609\/icwsm.v10i1.14816"},{"key":"2223_CR14","doi-asserted-by":"crossref","unstructured":"Kruk, J., Lubin, J., Sikka, K., Lin, X., Jurafsky, D., Divakaran, A.: Integrating text and image: Determining multimodal document intent in instagram posts (2019). arXiv preprint arXiv:1904.09073","DOI":"10.18653\/v1\/D19-1469"},{"key":"2223_CR15","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, S., Zhang, Y., Wang, D.: Multimodal sentiment detection based on multi-channel graph neural networks. In: 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), pp. 328\u2013339 (2021)","DOI":"10.18653\/v1\/2021.acl-long.28"},{"key":"2223_CR16","unstructured":"Zhang, B., Dai, G., Niu, F., Yin, N., Fan, X., Wang, S., Cao, X., Huang, H.: A survey of stance detection on social media: New directions and perspectives (2024). arXiv preprint arXiv:2409.15690"},{"key":"2223_CR17","doi-asserted-by":"crossref","unstructured":"Chu, Z., Chen, J., Chen, Q., Yu, W., He, T., Wang, H., Peng, W., Liu, M., Qin, B., Liu, T.: Navigate through enigmatic labyrinth a survey of chain of thought reasoning: advances, frontiers and future. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1173\u20131203 (2024)","DOI":"10.18653\/v1\/2024.acl-long.65"},{"key":"2223_CR18","doi-asserted-by":"crossref","unstructured":"Chen, W., Wang, W., Chu, Z., Ren, K., Zheng, Z., Lu, Z.: Self-para-consistency: Improving reasoning tasks at low cost for large language models. In: 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024), pp. 14162\u201314167. Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.findings-acl.842"},{"key":"2223_CR19","unstructured":"Liu, Y., Cao, J., Li, Z., He, R., Tan, T.: Breaking mental set to improve reasoning through diverse multi-agent debate. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"2223_CR20","doi-asserted-by":"crossref","unstructured":"Lan, X., Gao, C., Jin, D., Li, Y.: Stance detection with collaborative role-infused llm-based agents. In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 18, pp. 891\u2013903 (2024)","DOI":"10.1609\/icwsm.v18i1.31360"},{"key":"2223_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, B., Ma, J., Fu, X., Dai, G.: Logic augmented multi-decision fusion framework for stance detection on social media. Information Fusion, 103214 (2025)","DOI":"10.1016\/j.inffus.2025.103214"},{"key":"2223_CR22","doi-asserted-by":"crossref","unstructured":"Kawintiranon, K., Singh, L.: Knowledge enhanced masked language model for stance detection. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4725\u20134735 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.376"},{"key":"2223_CR23","doi-asserted-by":"crossref","unstructured":"Conforti, C., Berndt, J., Pilehvar, M.T., Giannitsarou, C., Toxvaerd, F., Collier, N.: Will-they-won\u2019t-they: A very large dataset for stance detection on twitter (2020). arXiv preprint arXiv:2005.00388","DOI":"10.18653\/v1\/2020.acl-main.157"},{"key":"2223_CR24","unstructured":"Devlin, J.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"2223_CR25","unstructured":"Liu, Y.: Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692364 (2019)"},{"key":"2223_CR26","doi-asserted-by":"crossref","unstructured":"Kawintiranon, K., Singh, L.: Polibertweet: a pre-trained language model for analyzing political content on twitter. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, pp. 7360\u20137367 (2022)","DOI":"10.63317\/28q9g62cdxvm"},{"key":"2223_CR27","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al.: Llama 2: Open foundation and fine-tuned chat models (2023). arXiv preprint arXiv:2307.09288"},{"key":"2223_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2223_CR29","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2223_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2223_CR31","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., Zhou, J.: Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"2223_CR32","doi-asserted-by":"crossref","unstructured":"Sobhani, P.e.a.: Dataset for Multi-target Stance Detection. In: EACL, pp. 551\u2013557 (2017)","DOI":"10.18653\/v1\/E17-2088"},{"key":"2223_CR33","doi-asserted-by":"crossref","unstructured":"Xu, R.e.a.: Overview of NLPCC Shared Task 4: Stance Detection in Chinese Microblogs. In: NLUIA, pp. 907\u2013916 (2016)","DOI":"10.1007\/978-3-319-50496-4_85"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02223-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02223-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02223-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T04:59:58Z","timestamp":1783313998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02223-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2223"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02223-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]},"assertion":[{"value":"22 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"237"}}