{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:53:52Z","timestamp":1763790832725,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533459","type":"print"},{"value":"9789819533466","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3346-6_4","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:49:38Z","timestamp":1763790578000},"page":"48-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Object Hallucination Through Assembled Chain-of-Thought Reasoning"],"prefix":"10.1007","author":[{"given":"Xinhao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xinyu","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Shengyong","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Lidia S.","family":"Chao","sequence":"additional","affiliation":[]},{"given":"Derek F.","family":"Wong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"4_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"An, W., et al.: Agla: mitigating object hallucinations in large vision-language models with assembly of global and local attention. arXiv preprint arXiv:2406.12718 (2024)","DOI":"10.1109\/CVPR52734.2025.02784"},{"key":"4_CR3","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Driving with LLMs: fusing object-level vector modality for explainable autonomous driving. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 14093\u201314100. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10611018"},{"issue":"12","key":"4_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5","volume":"67","author":"Z Chen","year":"2024","unstructured":"Chen, Z., et al.: How far are we to GPT-4v? Closing the gap to commercial multimodal models with open-source suites. Sci. China Inf. Sci. 67(12), 220101 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"4_CR7","unstructured":"Chuang, Y.S., Xie, Y., Luo, H., Kim, Y., Glass, J., He, P.: Dola: decoding by contrasting layers improves factuality in large language models. arXiv preprint arXiv:2309.03883 (2023)"},{"key":"4_CR8","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Thirty-seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=vvoWPYqZJA"},{"key":"4_CR9","unstructured":"Fu, C., et\u00a0al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Gunjal, A., Yin, J., Bas, E.: Detecting and preventing hallucinations in large vision language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 18135\u201318143 (2024)","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"4_CR11","doi-asserted-by":"publisher","unstructured":"Ho, N., Schmid, L., Yun, S.Y.: Large language models are reasoning teachers. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 14852\u201314882. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.830, https:\/\/aclanthology.org\/2023.acl-long.830","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: Opera: alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13418\u201313427 (2024)","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"4_CR13","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. NIPS \u201922. Curran Associates Inc., Red Hook, NY, USA (2024)"},{"key":"4_CR14","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":"4_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, X., Wen, J.R.: Evaluating object hallucination in large vision-language models. In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023). https:\/\/openreview.net\/forum?id=xozJw0kZXF","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"4_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"4_CR17","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Mitigating hallucination in large multi-modal models via robust instruction tuning. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"4_CR18","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Mitigating hallucination in large multi-modal models via robust instruction tuning. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=J44HfH4JCg"},{"key":"4_CR19","unstructured":"Liu, H., et al.: A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253 (2024)"},{"key":"4_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 (CVPR), pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"4_CR21","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 34892\u201334916. Curran Associates, Inc. (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"4_CR22","unstructured":"Mao, J., Qian, Y., Zhao, H., Wang, Y.: GPT-driver: learning to drive with GPT. In: NeurIPS 2023 Foundation Models for Decision Making Workshop (2023). https:\/\/openreview.net\/forum?id=Pvjk9lxLJK"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Mondal, D., Modi, S., Panda, S., Singh, R., Rao, G.S.: Kam-CoT: knowledge augmented multimodal chain-of-thoughts reasoning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 18798\u201318806 (2024)","DOI":"10.1609\/aaai.v38i17.29844"},{"key":"4_CR24","doi-asserted-by":"publisher","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4035\u20134045. Association for Computational Linguistics, Brussels, Belgium (2018). https:\/\/doi.org\/10.18653\/v1\/D18-1437, https:\/\/aclanthology.org\/D18-1437","DOI":"10.18653\/v1\/D18-1437"},{"key":"4_CR25","unstructured":"Sun, Z., et al.: Aligning large multimodal models with factually augmented RLHF (2024). https:\/\/openreview.net\/forum?id=B6t5wy6g5a"},{"key":"4_CR26","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"4_CR27","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"4_CR28","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=1PL1NIMMrw"},{"key":"4_CR29","unstructured":"Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models. In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K. (eds.) Advances in Neural Information Processing Systems (2022). https:\/\/openreview.net\/forum?id=_VjQlMeSB_J"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Drivegpt4: interpretable end-to-end autonomous driving via large language model. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3440097"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Yu, T., et\u00a0al.: RLHF-V: towards trustworthy MLLMs via behavior alignment from fine-grained correctional human feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13807\u201313816 (2024)","DOI":"10.1109\/CVPR52733.2024.01310"},{"issue":"8","key":"4_CR32","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3369699","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR33","unstructured":"Zhang, Z., Zhang, A., Li, M., Smola, A.: Automatic chain of thought prompting in large language models. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=5NTt8GFjUHkr"},{"key":"4_CR34","unstructured":"Zhang, Z., Zhang, A., Li, M., Zhao, H., Karypis, G., Smola, A.: Multimodal chain-of-thought reasoning in language models. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=y1pPWFVfvR"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, K., et al.: Regularized mask tuning: Uncovering hidden knowledge in pre-trained vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11663\u201311673 (2023)","DOI":"10.1109\/ICCV51070.2023.01071"},{"key":"4_CR36","unstructured":"Zhou, Y., Cui, C., Rafailov, R., Finn, C., Yao, H.: Aligning modalities in vision large language models via preference fine-tuning. In: ICLR 2024 Workshop on Reliable and Responsible Foundation Models (2024). https:\/\/openreview.net\/forum?id=GRGvC0rpA8"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3346-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:49:46Z","timestamp":1763790586000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3346-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533459","9789819533466"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3346-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}