{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T08:09:32Z","timestamp":1783930172889,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819235032","type":"print"},{"value":"9789819235049","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\/978-981-92-3504-9_17","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:35:52Z","timestamp":1783928152000},"page":"205-217","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Kesheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yamin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenqian","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjian","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"17_CR1","first-page":"8076","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"M Acharya","year":"2019","unstructured":"Acharya, M., Kafle, K., Kanan, C.: Tallyqa: answering complex counting questions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8076\u20138084 (2019)"},{"key":"17_CR2","first-page":"2425","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"S Antol","year":"2015","unstructured":"Antol, S. et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)"},{"key":"17_CR3","unstructured":"Bai, S., et al.: Qwen3-vl technical report. arXiv preprint https:\/\/arxiv.org\/abs\/2511.21631 (2025)"},{"key":"17_CR4","first-page":"10800","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Chen","year":"2020","unstructured":"Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10800\u201310809 (2020)"},{"key":"17_CR5","first-page":"14375","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"T Guan","year":"2024","unstructured":"Guan, T., et al.: Hallusionbench: an advanced diagnostic suite for entangled language hallucination and visual illusion in large vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14375\u201314385 (2024)"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"17_CR8","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: Benchmarking multimodal LLMs with generative comprehension. arXiv preprint https:\/\/arxiv.org\/abs\/2307.16125 (2023)"},{"key":"17_CR9","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. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language processing, pp. 292\u2013305 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"17_CR10","first-page":"216","volume-title":"European Conference on Computer Vision","author":"Y Liu","year":"2024","unstructured":"Liu, Y., et al.: MMbench: is your multi-modal model an all-around player? In: European Conference on Computer Vision, pp. 216\u2013233. Springer (2024)"},{"issue":"2","key":"17_CR11","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s40747-025-02184-1","volume":"12","author":"Y Liu","year":"2026","unstructured":"Liu, Y., Hu, Y., Chen, Z., Wang, S., Luo, W.: LLM-GA: a gradient-based multi-label adversarial attack by large language models. Complex Intell. Syst. 12(2), 71 (2026)","journal-title":"Complex Intell. Syst."},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Pham, K., et al.: Learning to predict visual attributes in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13018\u201313028 (2021)","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4035\u20134045 (2018)","DOI":"10.18653\/v1\/D18-1437"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Aligning large multimodal models with factually augmented RLHF. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 13088\u201313110 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"17_CR16","unstructured":"Yang, A., et al.: Qwen3 technical report. arXiv preprint https:\/\/arxiv.org\/abs\/2505.09388 (2025)"},{"key":"17_CR17","first-page":"17939","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Z Ye","year":"2026","unstructured":"Ye, Z., Luo, W., Zhou, Q., Tang, Y.: Reconstruction attack-resistant inference paradigm for LLM cloud services. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 17939\u201317947 (2026)"}],"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\/978-981-92-3504-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T07:35:55Z","timestamp":1783928155000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3504-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819235032","9789819235049"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3504-9_17","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"}}]}}