{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:36:35Z","timestamp":1758587795252,"version":"3.44.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060037","type":"print"},{"value":"9783032060044","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"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\/978-3-032-06004-4_32","type":"book-chapter","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:21:28Z","timestamp":1758561688000},"page":"320-330","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On the\u00a0Risk of\u00a0Misleading Reports: Diagnosing Textual Biases in\u00a0Multimodal Clinical AI"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3789-1957","authenticated-orcid":false,"given":"David","family":"Restrepo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6677-6547","authenticated-orcid":false,"given":"Ira","family":"Ktena","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0791-1264","authenticated-orcid":false,"given":"Maria","family":"Vakalopoulou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8773-1070","authenticated-orcid":false,"given":"Stergios","family":"Christodoulidis","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8500-788X","authenticated-orcid":false,"given":"Enzo","family":"Ferrante","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"32_CR1","unstructured":"Ambsdorf, J.: Benchmarking faithfulness: towards accurate natural language explanations in vision-language tasks. arXiv preprint arXiv:2304.08174 (2023)"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Atanasova, P., Camburu, O.M., Lioma, C., Lukasiewicz, T., Simonsen, J.G., Augenstein, I.: Faithfulness tests for natural language explanations. arXiv preprint arXiv:2305.18029 (2023)","DOI":"10.18653\/v1\/2023.acl-short.25"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 397\u2013406 (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"32_CR5","unstructured":"Chen, X., et al.: Janus-pro: unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:2501.17811 (2025)"},{"key":"32_CR6","unstructured":"Google: Medgemma hugging face. https:\/\/huggingface.co\/collections\/google\/medgemma-release-680aade845f90bec6a3f60c4 (2025), Accessed: [Insert Date Accessed 20 May 2025]"},{"key":"32_CR7","unstructured":"Grattafiori, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Kline, A., et al.: Multimodal machine learning in precision health: a scoping review. npj Digit. Med. 5(1), 171 (2022)","DOI":"10.1038\/s41746-022-00712-8"},{"key":"32_CR10","first-page":"28541","volume":"36","author":"C Li","year":"2023","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. Adv. Neural. Inf. Process. Syst. 36, 28541\u201328564 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR11","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":"32_CR12","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Luo, Y., et\u00a0al.: Fairclip: harnessing fairness in vision-language learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12289\u201312301 (2024)","DOI":"10.1109\/CVPR52733.2024.01168"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Parcalabescu, L., Frank, A.: Mm-shap: a performance-agnostic metric for measuring multimodal contributions in vision and language models & tasks. arXiv preprint arXiv:2212.08158 (2022)","DOI":"10.18653\/v1\/2023.acl-long.223"},{"key":"32_CR15","unstructured":"Parcalabescu, L., Frank, A.: Do vision & language decoders use images and text equally? how self-consistent are their explanations? arXiv preprint arXiv:2404.18624 (2024)"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Posocco, N., Bonnefoy, A.: Estimating expected calibration errors. In: International Conference on Artificial Neural Networks, pp. 139\u2013150. Springer (2021)","DOI":"10.1007\/978-3-030-86380-7_12"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Restrepo, D., et\u00a0al.: Multi-ophthalingua: a multilingual benchmark for assessing and debiasing llm ophthalmological qa in lmics. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 28321\u201328330 (2025)","DOI":"10.1609\/aaai.v39i27.35053"},{"key":"32_CR18","unstructured":"Stan, G.B.M., et al.: Lvlm-interpret: an interpretability tool for large vision-language models. arXiv preprint arXiv:2404.03118 (2024)"},{"key":"32_CR19","first-page":"74952","volume":"36","author":"M Turpin","year":"2023","unstructured":"Turpin, M., Michael, J., Perez, E., Bowman, S.: Language models don\u2019t always say what they think: unfaithful explanations in chain-of-thought prompting. Adv. Neural. Inf. Process. Syst. 36, 74952\u201374965 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Vig, J., Belinkov, Y.: Analyzing the structure of attention in a transformer language model. arXiv preprint arXiv:1906.04284 (2019)","DOI":"10.18653\/v1\/W19-4808"},{"key":"32_CR21","unstructured":"Wang, P., et\u00a0al.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Wu, J., Mooney, R.J.: Faithful multimodal explanation for visual question answering. arXiv preprint arXiv:1809.02805 (2018)","DOI":"10.18653\/v1\/W19-4812"},{"key":"32_CR23","doi-asserted-by":"publisher","unstructured":"Xia, P., et al.: RULE: reliable multimodal rag for factuality in medical vision language models. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 1081\u20131093. Association for Computational Linguistics, Miami, Florida, USA, November 2024. https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.62, https:\/\/aclanthology.org\/2024.emnlp-main.62\/","DOI":"10.18653\/v1\/2024.emnlp-main.62"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Positive-congruent training: towards regression-free model updates. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14299\u201314308 (2021)","DOI":"10.1109\/CVPR46437.2021.01407"},{"issue":"1","key":"32_CR25","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1038\/s43856-024-00601-z","volume":"4","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Liu, X., Jin, Q., Huang, F., Lu, Z.: Unmasking and quantifying racial bias of large language models in medical report generation. Commun. Med. 4(1), 176 (2024)","journal-title":"Commun. Med."},{"key":"32_CR26","unstructured":"Zhang, Y.F., et al.: Debiasing multimodal large language models. arXiv preprint arXiv:2403.05262 (2024)"}],"container-title":["Lecture Notes in Computer Science","AI for Clinical Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06004-4_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:21:39Z","timestamp":1758561699000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06004-4_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"ISBN":["9783032060037","9783032060044"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06004-4_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"22 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"CMLLMs","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Multimodal Large Language Models in Clinical Practice","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cmllms2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clinicalmllms.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}