{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T15:07:03Z","timestamp":1768316823058,"version":"3.49.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731945","type":"print"},{"value":"9783031731952","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73195-2_8","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T10:02:10Z","timestamp":1732615330000},"page":"127-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["The First to\u00a0Know: How Token Distributions Reveal Hidden Knowledge in\u00a0Large Vision-Language Models?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0245-1676","authenticated-orcid":false,"given":"Qinyu","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-0582","authenticated-orcid":false,"given":"Ming","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1002-5645","authenticated-orcid":false,"given":"Kartik","family":"Gupta","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6871-346X","authenticated-orcid":false,"given":"Akshay","family":"Asthana","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1464-9500","authenticated-orcid":false,"given":"Liang","family":"Zheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8929-7899","authenticated-orcid":false,"given":"Stephen","family":"Gould","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"8_CR1","unstructured":"Burns, C., Ye, H., Klein, D., Steinhardt, J.: Discovering latent knowledge in language models without supervision. arXiv preprint arXiv:2212.03827 (2022)"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Sikka, K., Cogswell, M., Ji, H., Divakaran, A.: DRESS: instructing large vision-language models to align and interact with humans via natural language feedback. arXiv preprint arXiv:2311.10081 (2023)","DOI":"10.1109\/CVPR52733.2024.01350"},{"key":"8_CR3","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"8_CR4","unstructured":"Durmus, E., et\u00a0al.: Towards measuring the representation of subjective global opinions in language models. arXiv preprint arXiv:2306.16388 (2023)"},{"key":"8_CR5","unstructured":"Gao, P., et\u00a0al.: LLaMA-Adapter v2: parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010 (2023)"},{"key":"8_CR6","unstructured":"Ging, S., Bravo, M.A., Brox, T.: Open-ended VQA benchmarking of vision-language models by exploiting classification datasets and their semantic hierarchy. arXiv preprint arXiv:2402.07270 (2024)"},{"key":"8_CR7","unstructured":"Gong, T., et al.: MultiModal-GPT: a vision and language model for dialogue with humans. arXiv preprint arXiv:2305.04790 (2023)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: VizWiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"8_CR9","unstructured":"Gurnee, W., Tegmark, M.: Language models represent space and time. arXiv preprint arXiv:2310.02207 (2023)"},{"key":"8_CR10","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"8_CR11","unstructured":"Li, K., Patel, O., Vi\u00e9gas, F., Pfister, H., Wattenberg, M.: Inference-time intervention: eliciting truthful answers from a language model. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR12","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. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"8_CR13","unstructured":"Liang, P., et\u00a0al.: Holistic evaluation of language models. arXiv preprint arXiv:2211.09110 (2022)"},{"key":"8_CR14","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":"8_CR15","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"8_CR16","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR17","unstructured":"Liu, X., Zhu, Y., Lan, Y., Yang, C., Qiao, Y.: Query-relevant images jailbreak large multi-modal models. arXiv preprint arXiv:2311.17600 (2023)"},{"key":"8_CR18","unstructured":"Lu, P., et al.: MathVista: evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Pi, R., et al.: MLLM-Protector: Ensuring MLLM\u2019s safety without hurting performance. arXiv preprint arXiv:2401.02906 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.895"},{"key":"8_CR20","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Qian, C., et al.: Towards tracing trustworthiness dynamics: revisiting pre-training period of large language models. arXiv preprint arXiv:2402.19465 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.290"},{"key":"8_CR22","unstructured":"Qian, Y., Zhang, H., Yang, Y., Gan, Z.: How easy is it to fool your multimodal LLMs? An empirical analysis on deceptive prompts. arXiv preprint arXiv:2402.13220 (2024)"},{"key":"8_CR23","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"8_CR24","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet: large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Slobodkin, A., Goldman, O., Caciularu, A., Dagan, I., Ravfogel, S.: The curious case of hallucinatory (un)answerability: finding truths in the hidden states of over-confident large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 3607\u20133625 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.220"},{"key":"8_CR26","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Tjuatja, L., Chen, V., Wu, S.T., Talwalkar, A., Neubig, G.: Do LLMs exhibit human-like response biases? a case study in survey design. arXiv preprint arXiv:2311.04076 (2023)","DOI":"10.1162\/tacl_a_00685"},{"key":"8_CR28","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"8_CR29","unstructured":"Touvron, H., et\u00a0al.: LLaMA2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Liao, Y., Liu, H., Liu, H., Wang, Y., Wang, Y.: MM-SAP: a comprehensive benchmark for assessing self-awareness of multimodal large language models in perception. arXiv preprint arXiv:2401.07529 (2024)","DOI":"10.18653\/v1\/2024.acl-long.498"},{"key":"8_CR31","unstructured":"Yang, Z., et al: The dawn of LMMs: preliminary explorations with GPT-4V(ision). arXiv preprint arXiv:2309.17421 (2023)"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: mPLUG-Owl2: revolutionizing multi-modal large language model with modality collaboration. arXiv preprint arXiv:2311.04257 (2023)","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"8_CR33","unstructured":"Zhao, H., Zhang, M., Zhao, W., Ding, P., Huang, S., Wang, D.: Cobra: extending mamba to multi-modal large language model for efficient inference. arXiv preprint arXiv:2403.14520 (2024)"},{"key":"8_CR34","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":"8_CR35","unstructured":"Zou, A., et\u00a0al.: Representation engineering: a top-down approach to AI transparency. arXiv preprint arXiv:2310.01405 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73195-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T01:03:06Z","timestamp":1733101386000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73195-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031731945","9783031731952"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73195-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}