{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:06:00Z","timestamp":1789207560011,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","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\/978-3-032-37335-9_23","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:13:00Z","timestamp":1789204380000},"page":"421-437","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Proximity-Constrained Counterfactual Decoding for\u00a0Hallucination-Robust Medical VQA"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9749-7858","authenticated-orcid":false,"given":"Dwarikanath","family":"Mahapatra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2553-0061","authenticated-orcid":false,"given":"Abhijit","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manish","family":"Pandey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joy","family":"Dhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudipta","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyuan","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Behzad","family":"Bozorgtabar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3930-6600","authenticated-orcid":false,"given":"Imran","family":"Razzak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"23_CR1","unstructured":"An, W., et al.: AGLA: attention-guided local and global alignment for faithful multimodal generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)"},{"key":"23_CR2","unstructured":"Asadi, M., Nedaee, T., O\u2019Sullivan, J.W., Ashley, E., Adeli, E.: Deterministic hallucination detection in medical vqa via confidence-evidence bayesian gain. arXiv preprint arXiv:2603.21693 (2026)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network dissection: Quantifying interpretability of deep visual representations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6541\u20136549 (2017)","DOI":"10.1109\/CVPR.2017.354"},{"key":"23_CR4","unstructured":"Chen, Z., Zhao, Z., Luo, H., Yao, H., Li, B., Zhou, J.: HALC: object hallucination reduction via adaptive focal-contrast decoding. In: Proceedings of the 41st International Conference on Machine Learning (ICML) (2024). https:\/\/arxiv.org\/abs\/2403.00425, arXiv:2403.00425"},{"key":"23_CR5","unstructured":"Chen, Z., Varma, M., Xu, J., Paschali, M., et\u00a0al.: A vision-language foundation model to enhance efficiency of chest x-ray interpretation (2024). https:\/\/arxiv.org\/abs\/2401.12208"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Cohen, R., Hamri, M., Geva, M., Globerson, A.: Lm vs lm: detecting factual errors via cross examination. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 12621\u201312640 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.778"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Deperrois, N., et al.: Radvlm: a multitask conversational vision-language model for radiology (2025). arXiv preprintarXiv:2502.03333","DOI":"10.1038\/s41598-026-66181-1"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Hu, X., et al.: Expert knowledge-aware image difference graph representation learning for difference-aware medical visual question answering. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4156\u20134165 (2023)","DOI":"10.1145\/3580305.3599819"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Irvin, J., et\u00a0al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. arXiv preprint arXiv:1901.07031 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Khanal, B., et al.: Hallucination-aware multimodal benchmark for gastrointestinal image analysis with large vision\u2013language models. In: Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2025. LNCS (2025)","DOI":"10.1007\/978-3-032-05127-1_23"},{"key":"23_CR14","doi-asserted-by":"publisher","unstructured":"Kuhn, L., Farquhar, S., Kossen, J., Gal, Y., et\u00a0al.: Detecting hallucinations in large language models using semantic entropy. Nature 630 (2024). https:\/\/doi.org\/10.1038\/s41586-024-07421-0, https:\/\/www.nature.com\/articles\/s41586-024-07421-0","DOI":"10.1038\/s41586-024-07421-0"},{"key":"23_CR15","doi-asserted-by":"publisher","unstructured":"Lau, J.J., Gayen, S., Ben\u00a0Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Scientific Data 5, 180251 (2018). https:\/\/doi.org\/10.1038\/sdata.2018.251, https:\/\/www.nature.com\/articles\/sdata2018251.pdf","DOI":"10.1038\/sdata.2018.251"},{"key":"23_CR16","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 (CVPR), pp. 13872\u201313882 (2024). https:\/\/openaccess.thecvf.com\/content\/CVPR2024\/papers\/Leng_Mitigating_Object_Hallucinations_in_Large_Vision-Language_Models_through_Visual_Contrastive_CVPR_2024_paper.pdf","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"23_CR17","unstructured":"Li, C., et al.: LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. In: NeurIPS Datasets and Benchmarks (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/hash\/5abcdf8ecdcacba028c6662789194572-Abstract-Datasets_and_Benchmarks.html"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Liao, Z., Hu, S., Zou, K., Fu, H., Zhen, L., Xia, Y.: Vision-amplified semantic entropy for hallucination detection in medical visual question answering. In: Proceedings of Medical Image Computing and Computer Assisted Intervention - MICCAI 2025. LNCS, vol. 15964. Springer, Switzerland (2025)","DOI":"10.1007\/978-3-032-04971-1_63"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Ostmeier, S., et al.: GREEN: generative radiology report evaluation and error notation. arXiv preprint arXiv:2405.03595 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.21"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626 (2017). https:\/\/openaccess.thecvf.com\/content_iccv_2017\/html\/Selvaraju_Grad-CAM_Visual_Explanations_ICCV_2017_paper.html","DOI":"10.1109\/ICCV.2017.74"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Suo, W., Zhang, L., Sun, M., Wu, L.Y., Wang, P., Zhang, Y.: Octopus: alleviating hallucination via dynamic contrastive decoding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 29904\u201329914 (2025)","DOI":"10.1109\/CVPR52734.2025.02783"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Wu, Y., et al.: Antidote: a unified framework for mitigating LVLM hallucinations in counterfactual presupposition and object perception. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025). https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/papers\/Wu_Antidote_A_Unified_Framework_for_Mitigating_LVLM_Hallucinations_in_Counterfactual_CVPR_2025_paper.pdf","DOI":"10.1109\/CVPR52734.2025.01365"},{"key":"23_CR23","unstructured":"Yan, Q., et al.: Medhalltune: an instruction-tuning benchmark for mitigating medical hallucination in vision-language models. arXiv preprint arXiv:2502.20780 (2025). https:\/\/arxiv.org\/abs\/2502.20780"},{"key":"23_CR24","unstructured":"Yang, T., Li, Z., Cao, J., Xu, C.: Understanding and mitigating hallucination in large vision-language models via modular attribution and intervention. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Zhan, C., et al.: Debiasing medical visual question answering via counterfactual training. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 382\u2013393. Springer (2023)","DOI":"10.1007\/978-3-031-43895-0_36"},{"key":"23_CR26","unstructured":"Zhang, S., Sambara, S., Banerjee, O., Acosta, J.N., Fahrner, L.J., Rajpurkar, P.: Radflag: a black-box hallucination detection method for medical vision language models. In: Hegselmann, S., et al. (eds.) Proceedings of the 4th Machine Learning for Health Symposium. Proceedings of Machine Learning Research, vol.\u00a0259, pp. 1087\u20131103. PMLR (15\u201316 Dec 2025)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Zhuang, X., Zhu, Z., Xie, Y., Liang, L., Zou, Y.: Vasparse: towards efficient visual hallucination mitigation via visual-aware token sparsification. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 4189\u20134199 (2025)","DOI":"10.1109\/CVPR52734.2025.00396"}],"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\/978-3-032-37335-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:13:08Z","timestamp":1789204388000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_23","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":"13 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"}}]}}