{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T03:13:45Z","timestamp":1792725225213,"version":"4.5.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371737","type":"print"},{"value":"9783032371744","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-37174-4_3","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:01:12Z","timestamp":1789714872000},"page":"36-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Delineating Knowledge Boundaries for\u00a0Honest Large Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Junru","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huining","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhen","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuntao","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"3_CR1","unstructured":"Bi, J., et al.: Prism: self-pruning intrinsic selection method for training-free multimodal data selection. arXiv preprint arXiv:2502.12119 (2025)"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Bi, J., et al.: Llava steering: visual instruction tuning with 500x fewer parameters through modality linear representation-steering. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15230\u201315250 (2025)","DOI":"10.18653\/v1\/2025.acl-long.739"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"49706","DOI":"10.52202\/079017-1573","volume":"37","author":"F Brahman","year":"2024","unstructured":"Brahman, F., et al.: The art of saying no: contextual noncompliance in language models. Adv. Neural. Inf. Process. Syst. 37, 49706\u201349748 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Can pre-trained vision and language models answer visual information-seeking questions?. arXiv abs\/2302.11713 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Can pre-trained vision and language models answer visual information-seeking questions? In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 14948\u201314968 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"3_CR6","unstructured":"Cheng, Q., et al.: Can AI assistants know what they don\u2019t know? In: Proceedings of the 41st International Conference on Machine Learning. ICML 2024. JMLR.org (2024)"},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"49250","DOI":"10.52202\/075280-2142","volume":"36","author":"W Dai","year":"2023","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 49250\u201349267 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gurari, D., Li, Q., Stangl, A., Guo, A., Lin, C.: Vizwiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"3_CR10","unstructured":"Hills, J., Anadkat, S.: Using logprobs. OpenAI Cookbook (2023). https:\/\/cookbook.openai.com\/examples\/using_logprobs"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Hong, J., Lee, N., Thorne, J.: ORPO: monolithic preference optimization without reference model. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 11170\u201311189 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.626"},{"key":"3_CR12","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"3_CR13","first-page":"1","volume":"43","author":"L Huang","year":"2023","unstructured":"Huang, L., et al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst. 43, 1\u201355 (2023)","journal-title":"ACM Trans. Inf. Syst."},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Benchmarking multimodal knowledge conflict for large multimodal models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a040, pp. 22283\u201322291 (2026)","DOI":"10.1609\/aaai.v40i27.39385"},{"key":"3_CR15","unstructured":"Jiang, K., et al.: When large multimodal models confront evolving knowledge: challenges and explorations. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"3_CR16","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: Conference on Empirical Methods in Natural Language Processing (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Lin, S.C., Hilton, J., Evans, O.: Truthfulqa: measuring how models mimic human falsehoods. In: Annual Meeting of the Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"3_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. arXiv preprint arXiv:2306.14565 (2023)"},{"key":"3_CR19","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv abs\/2304.08485 (2023)"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: Advances in Neural Information Processing Systems, pp. 2507\u20132521 (2022)","DOI":"10.52202\/068431-0182"},{"key":"3_CR22","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":"3_CR23","doi-asserted-by":"crossref","unstructured":"Ouali, Y., Bulat, A., Martinez, B., Tzimiropoulos, G.: CLIP-DPO: vision-language models as a source of preference for fixing hallucinations in LVLMs. In: European Conference on Computer Vision, pp. 395\u2013413. Springer (2024)","DOI":"10.1007\/978-3-031-73116-7_23"},{"key":"3_CR24","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural. Inf. Process. Syst. 36, 53728\u201353741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"3_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12200-022-00055-y","volume":"16","author":"M Tan","year":"2023","unstructured":"Tan, M., et al.: Co-packaged optics (CPO): status, challenges, and solutions. Front. Optoelectron. 16(1), 1 (2023)","journal-title":"Front. Optoelectron."},{"key":"3_CR26","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":"3_CR27","unstructured":"Wang, Y., et al.: Drawing the line: enhancing trustworthiness of MLLMs through the power of refusal. arXiv preprint arXiv:2412.11196 (2024)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Xie, Y., Li, G., Xu, X., Kan, M.Y.: V-DPO: mitigating hallucination in large vision language models via vision-guided direct preference optimization. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 13258\u201313273 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.775"},{"issue":"12","key":"3_CR29","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. SCIENCE CHINA Inf. Sci. 67(12), 220105 (2024)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: 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"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: R-tuning: instructing large language models to say \u2018i don\u2019t know\u2019. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 7113\u20137139 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.394"},{"key":"3_CR32","unstructured":"Zhang, T., Liu, F., Wong, J., Abbeel, P., Gonzalez, J.E.: The wisdom of hindsight makes language models better instruction followers. In: International Conference on Machine Learning, pp. 41414\u201341428. PMLR (2023)"},{"key":"3_CR33","unstructured":"Zhang, X., et al.: PMC-VQA: visual instruction tuning for medical visual question answering. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 2507\u20132517 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37174-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T07:01:27Z","timestamp":1789714887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37174-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371737","9783032371744"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37174-4_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"19 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}