{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:17:30Z","timestamp":1781587050900,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569625","type":"print"},{"value":"9789819569632","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\/978-981-95-6963-2_6","type":"book-chapter","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:09:01Z","timestamp":1770372541000},"page":"72-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["PRSM: A Measure to\u00a0Evaluate CLIP\u2019s Robustness Against Paraphrases"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8266-0162","authenticated-orcid":false,"given":"Udo","family":"Schlegel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6447-8671","authenticated-orcid":false,"given":"Franziska","family":"Weeber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4861-1412","authenticated-orcid":false,"given":"Thomas","family":"Seidl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,7]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Ceron, T., Falk, N., Bari\u0107, A., Nikolaev, D., Pad\u00f3, S.: Beyond prompt brittleness: evaluating the reliability and consistency of political worldviews in LLMs. Trans. Assoc. Comput. Linguist. (2024)","DOI":"10.1162\/tacl_a_00710"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Gonen, H., Iyer, S., Blevins, T., Smith, N., Zettlemoyer, L.: Demystifying prompts in language models via perplexity estimation. In: Findings of the Association for Computational Linguistics (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.679"},{"key":"6_CR3","unstructured":"Grattafiori, A., et\u00a0al.: The LLaMA 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"6_CR4","unstructured":"Guan, J., Ding, T., Cao, L., Pan, L., Wang, C., Zheng, X.: Probing the robustness of vision-language pretrained models: a multimodal adversarial attack approach. arXiv preprint arXiv:2408.13461 (2024)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Howard, P., Madasu, A., Le, T., Moreno, G.L., Bhiwandiwalla, A., Lal, V.: SocialCounterFactuals: probing and mitigating intersectional social biases in vision-language models with counterfactual examples. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01138"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Jin, D., Jin, Z., Tianyi\u00a0Zhou, J., Szolovits, P.: Is BERT really robust? A strong baseline for natural language attack on text classification and entailment. In: AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Jung, D., Lee, S., Moon, H., Park, C., Lim, H.: FLEX: a benchmark for evaluating robustness of fairness in large language models. In: Findings of the Association for Computational Linguistics (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.199"},{"key":"6_CR8","unstructured":"Lan, J., et al.: My answer is not \u2018fair\u2019: mitigating social bias in vision-language models via fair and biased residuals. arXiv preprint arXiv:2505.23798 (2025)"},{"key":"6_CR9","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International conference on machine learning. PMLR (2022)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Li, L., Ma, R., Guo, Q., Xue, X., Qiu, X.: BERT-ATTACK: adversarial attack against BERT using BERT. In: Empirical Methods in Natural Language Processing (EMNLP) (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.500"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Luo, Y., et\u00a0al.: FairCLIP: harnessing fairness in vision-language learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12289\u201312301 (2024)","DOI":"10.1109\/CVPR52733.2024.01168"},{"key":"6_CR12","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Rossetto, L., et\u00a0al.: Interactive video retrieval in the age of deep learning\u2013detailed evaluation of VBS 2019. IEEE Trans. Multimedia (2020)","DOI":"10.1109\/TMM.2020.2980944"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"R\u00f6ttger, P., et al.: Political compass or spinning arrow? Towards more meaningful evaluations for values and opinions in large language models. In: Annual Meeting of the Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.acl-long.816"},{"key":"6_CR15","unstructured":"Sclar, M., Choi, Y., Tsvetkov, Y., Suhr, A.: Quantifying language models\u2019 sensitivity to spurious features in prompt design or: how i learned to start worrying about prompt formatting. In: International Conference on Learning Representations (2024)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Shu, B., et al.: You don\u2019t need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments. In: North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2024)","DOI":"10.18653\/v1\/2024.naacl-long.295"},{"key":"6_CR17","unstructured":"Wang, B., et al.: Adversarial GLUE: a multi-task benchmark for robustness evaluation of language models. In: Advances in Neural Information Processing Systems: Track on Datasets and Benchmarks (2021)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et\u00a0al.: Robust fine-tuning of zero-shot models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"6_CR19","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? arXiv preprint arXiv:2210.01936 (2022)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6963-2_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:09:05Z","timestamp":1770372545000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6963-2_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569625","9789819569632"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6963-2_6","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":"7 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}