{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T09:02:16Z","timestamp":1789722136048,"version":"4.0.1"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374219","type":"print"},{"value":"9783032374226","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\/978-3-032-37422-6_10","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:14:02Z","timestamp":1789719242000},"page":"154-177","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["See Only When Needed: Context-Aware Attention Intervention for\u00a0Mitigating Hallucinations in\u00a0LVLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4669-3774","authenticated-orcid":false,"given":"Yuqing","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8962-0448","authenticated-orcid":false,"given":"Wenbo","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7537-6457","authenticated-orcid":false,"given":"Yingjun","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5213-0462","authenticated-orcid":false,"given":"Xiantong","family":"Zhen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9092-1556","authenticated-orcid":false,"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8264-6117","authenticated-orcid":false,"given":"Ling","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"10_CR1","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":"10_CR2","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"10_CR3","unstructured":"Bai, Z., Wang, P., Xiao, T., He, T., Han, Z., Zhang, Z., Shou, M.Z.: Hallucination of multimodal large language models: A survey. arXiv preprint arXiv:2404.18930 (2024)"},{"key":"10_CR4","doi-asserted-by":"publisher","first-page":"7400","DOI":"10.52202\/079017-0237","volume":"37","author":"S Basu","year":"2024","unstructured":"Basu, S., Grayson, M., Morrison, C., Nushi, B., Feizi, S., Massiceti, D.: Understanding information storage and transfer in multi-modal large language models. Adv. Neural. Inf. Process. Syst. 37, 7400\u20137426 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: Ict: Image-object cross-level trusted intervention for mitigating object hallucination in large vision-language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4209\u20134221 (2025)","DOI":"10.1109\/CVPR52734.2025.00398"},{"key":"10_CR7","unstructured":"Chen, Z., et al.: Mitigating hallucination in visual language models with visual supervision. arXiv preprint arXiv:2311.16479 (2023)"},{"issue":"240","key":"10_CR8","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: Palm: Scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"10_CR9","unstructured":"Chuang, Y.S., Xie, Y., Luo, H., Kim, Y., Glass, J.R., He, P.: Dola: Decoding by contrasting layers improves factuality in large language models. In: International Conference on Learning Representations, vol. 2024, pp. 54158\u201354183 (2024)"},{"key":"10_CR10","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":"10_CR11","doi-asserted-by":"crossref","unstructured":"Favero, A., Zancato, L., Trager, M., Choudhary, S., Perera, P., Achille, A., Swaminathan, A., Soatto, S.: 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":"10_CR12","doi-asserted-by":"crossref","unstructured":"Guan, T., et\u00a0al.: 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)","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"10_CR13","unstructured":"Huang, W., et al.: Vision-r1: Incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749 (2025)"},{"key":"10_CR14","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":"10_CR15","unstructured":"Huo, F., Xu, W., Zhang, Z., Wang, H., Chen, Z., Zhao, P.: Self-introspective decoding: Alleviating hallucinations for large vision-language models. arXiv preprint arXiv:2408.02032 (2024)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, C., et al.: Hallucination augmented contrastive learning for multimodal large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27036\u201327046 (2024)","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"10_CR17","unstructured":"Lee, S., Park, S.H., Jo, Y., Seo, M.: Volcano: mitigating multimodal hallucination through self-feedback guided revision. In: Proceedings of the 2023 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (2023)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Leng, S., Zhang, H., Chen, G., Li, X., Lu, S., Miao, C., Bing, L.: 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":"10_CR19","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"10_CR20","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"10_CR21","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 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"10_CR22","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. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"10_CR23","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":"10_CR24","unstructured":"Liu, H., et al.: A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253 (2024)"},{"key":"10_CR25","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":"10_CR26","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":"10_CR27","unstructured":"Liu, S., Ye, H., Zou, J.: Reducing hallucinations in large vision-language models via latent space steering. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"10_CR28","doi-asserted-by":"publisher","unstructured":"Liu, S., Zheng, K., Chen, W.: Paying more attention to image: A training-free method for alleviating hallucination in lvlms. In: European Conference on Computer Vision, pp. 125\u2013140. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73010-8_8","DOI":"10.1007\/978-3-031-73010-8_8"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Visual-rft: Visual reinforcement fine-tuning. arXiv preprint arXiv:2503.01785 (2025)","DOI":"10.1109\/ICCV51701.2025.00197"},{"key":"10_CR30","unstructured":"Neo, C., Ong, L., Torr, P., Geva, M., Krueger, D., Barez, F.: Towards interpreting visual information processing in vision-language models. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"10_CR31","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.52202\/068431-2011","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 4035\u20134045 (2018)","DOI":"10.18653\/v1\/D18-1437"},{"key":"10_CR33","doi-asserted-by":"publisher","unstructured":"Schwenk, D., Khandelwal, A., Clark, C., Marino, K., Mottaghi, R.: A-okvqa: A benchmark for visual question answering using world knowledge. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) European Conference on Computer Vision, pp. 146\u2013162. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20074-8_9","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"10_CR34","unstructured":"Shen, H., et\u00a0al.: Vlm-r1: A stable and generalizable r1-style large vision-language model. arXiv preprint arXiv:2504.07615 (2025)"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: Videobert: A joint model for video and language representation learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7464\u20137473 (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Sun, Z., et\u00a0al.: Aligning large multimodal models with factually augmented rlhf. arXiv preprint arXiv:2309.14525 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Tan, H., et al.: Reason-rft: Reinforcement fine-tuning for visual reasoning. arXiv preprint arXiv:2503.20752 (2025)","DOI":"10.52202\/085713-0204"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Tang, F., et\u00a0al.: Seeing far and clearly: Mitigating hallucinations in mllms with attention causal decoding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26147\u201326159 (2025)","DOI":"10.1109\/CVPR52734.2025.02435"},{"key":"10_CR39","unstructured":"Team, Q.: Qwen3.5: Accelerating productivity with native multimodal agents (2026). https:\/\/qwen.ai\/blog?id=qwen3.5"},{"key":"10_CR40","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Wan, Z., et al.: Only: One-layer intervention sufficiently mitigates hallucinations in large vision-language models. In: Proceedings of the International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.00309"},{"key":"10_CR42","unstructured":"Wu, Y., et al.: Overcoming language priors in visual question answering via distinguishing superficially similar instances. Proceedings of the 29th International Conference on Computational Linguistics, pp. 5721\u20135729 (2022)"},{"key":"10_CR43","unstructured":"Ye, Q., et\u00a0al.: mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Yin, S., et al.: A survey on multimodal large language models. Natl. Sci. Rev. 11(12), nwae403 (2024)","DOI":"10.1093\/nsr\/nwae403"},{"key":"10_CR45","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":"10_CR46","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":"10_CR47","doi-asserted-by":"crossref","unstructured":"Yue, Z., Zhang, L., Jin, Q.: Less is more: Mitigating multimodal hallucination from an eos decision perspective. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, pp. 11766\u201311781 (2024)","DOI":"10.18653\/v1\/2024.acl-long.633"},{"key":"10_CR48","unstructured":"Zhang, X., et\u00a0al.: Hallucination begins where saliency drops. arXiv preprint arXiv:2601.20279 (2026)"},{"key":"10_CR49","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":"10_CR50","unstructured":"Zhou, H., Li, X., Wang, R., Cheng, M., Zhou, T., Hsieh, C.J.: R1-zero\u2019s \u201caha moment\" in visual reasoning on a 2b non-sft model. arXiv preprint arXiv:2503.05132 (2025)"},{"key":"10_CR51","unstructured":"Zhou, Y., et al.: Analyzing and mitigating object hallucination in large vision-language models. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"10_CR52","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"10_CR53","unstructured":"Zou, X., et al.: Look twice before you answer: Memory-space visual retracing for hallucination mitigation in multimodal large language models. In: The Forty-second International Conference on Machine Learning (ICML) (2025)"}],"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\/978-3-032-37422-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:14:19Z","timestamp":1789719259000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37422-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374219","9783032374226"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37422-6_10","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"}}]}}