{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:10:17Z","timestamp":1783930217424,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234318","type":"print"},{"value":"9789819234325","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3432-5_43","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:39:39Z","timestamp":1783928379000},"page":"529-540","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Att-VCD: Mitigating Hallucination in MLLMs via Attention-Guided Visual Contrastive Decoding"],"prefix":"10.1007","author":[{"given":"Chi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Licheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheren","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"43_CR1","unstructured":"Liu, H., Zhang, C., Xu, Y., Wang, J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"43_CR2","unstructured":"Bai, Y., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2309.15103 (2023)"},{"key":"43_CR3","unstructured":"Alayrac, J.-B., et al.: Flamingo: a visual language model for few-shot learning. arXiv preprint arXiv:2204.14198 (2022)"},{"key":"43_CR4","unstructured":"Chen, W., Wu, S., Wang, X., Zeng, H., et al.: InternVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. arXiv preprint arXiv:2312.14238 (2023)"},{"key":"43_CR5","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Aligning large multi-modal model with robust instruction tuning. CoRR (2023)"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Leng, S., et al.: Mitigating object hallucinations in large vision-language models through visual contrastive decoding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13872\u201313882 (2024)","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"43_CR7","unstructured":"Chen, C., et al.: PerturboLLaVA: reducing multimodal hallucinations with perturbative visual training. arXiv preprint arXiv:2503.06486 (2025)"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Favero, A., et al.: Multi-modal hallucination control by visual information grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14303\u201314312 (2024)","DOI":"10.1109\/CVPR52733.2024.01356"},{"key":"43_CR9","doi-asserted-by":"publisher","first-page":"133571","DOI":"10.52202\/079017-4246","volume":"37","author":"J Kim","year":"2024","unstructured":"Kim, J., Kim, H., Yeonju, K., Ro, Y.M.: Code: contrasting self-generated description to combat hallucination in large multi-modal models. Adv. Neural. Inf. Process. Syst. 37, 133571\u2013133599 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"43_CR10","unstructured":"Bai, Z., et al.: Hallucination of multimodal large language models: a survey. arXiv preprint arXiv:2404.18930 (2024)"},{"key":"43_CR11","unstructured":"Zhang, J., Khayatkhoei, M., Chhikara, P., Ilievski, F.: Mllms know where to look: training-free perception of small visual details with multimodal LLMS. arXiv preprint arXiv:2502.17422 (2025)"},{"key":"43_CR12","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s11263-025-02607-z","volume":"134","author":"C Tu","year":"2026","unstructured":"Tu, C., et al.: Attention reallocation: towards zero-cost and controllable hallucination mitigation of mllms. Int. J. Comput. Vision 134, 22 (2026)","journal-title":"Int. J. Comput. Vision"},{"key":"43_CR13","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Mitigating hallucination in large multi-modal models via robust instruction tuning. arXiv preprint arXiv:2306.14565 (2023)"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Yu, Q., et al.: Hallucidoctor: mitigating hallucinatory toxicity in visual instruction data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12944\u201312953 (2024)","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"43_CR15","unstructured":"Sarkar, P., Ebrahimi, S., Etemad, A., Beirami, A., Ar\u0131k, S.\u00d6., Pfister, T.: Mitigating object hallucination in MLLMs via data-augmented phrase-level alignment. arXiv preprint arXiv:2405.18654 (2024)"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Wang, X., Pan, J., Ding, L., Biemann, C.: Mitigating hallucinations in large vision-language models with instruction contrastive decoding. arXiv preprint arXiv:2403.18715 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"43_CR17","doi-asserted-by":"crossref","unstructured":"An, W., et al.: Mitigating object hallucinations in large vision-language models with assembly of global and local attention. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29915\u201329926 (2025)","DOI":"10.1109\/CVPR52734.2025.02784"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.-R.: Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"43_CR19","unstructured":"Wang, J., et al.: Amber: an LLM-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv preprint arXiv:2311.07397 (2023)"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"43_CR21","unstructured":"Bai, S., et al: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"43_CR22","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x","volume":"67","author":"S Yin","year":"2024","unstructured":"Yin, S., et al.: Woodpecker: hallucination correction for multimodal large language models. Sci. China Inf. Sci. 67, 220105 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"43_CR23","unstructured":"Li, J., Zhang, J., Jie, Z., Ma, L., Li, G.: Mitigating hallucination for large vision language model by inter-modality correlation calibration decoding. arXiv preprint arXiv:2501.01926 (2025)"},{"key":"43_CR24","unstructured":"Zhao, Z., Wang, B., Ouyang, L., Dong, X., Wang, J., He, C.: Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization. arXiv preprint arXiv:2311.16839 (2023)"},{"key":"43_CR25","unstructured":"Cho, Y., Kim, K., Hwang, T., Cho, S.: Do you keep an eye on what i ask? Mitigating multimodal hallucination via attention-guided ensemble decoding. arXiv preprint arXiv:2505.17529 (2025)"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards vqa models that can read. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3432-5_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:39:42Z","timestamp":1783928382000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3432-5_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234318","9789819234325"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3432-5_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}