{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T18:05:51Z","timestamp":1789236351865,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375490","type":"print"},{"value":"9783032375506","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\/978-3-032-37550-6_20","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:22:42Z","timestamp":1789233762000},"page":"339-356","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DEX-AR: A Dynamic Explainability Method for\u00a0Autoregressive Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Walid","family":"Bousselham","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angie","family":"Boggust","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hendrik","family":"Strobelt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hilde","family":"Kuehne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. ACL (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"20_CR2","unstructured":"Achiam, J., et al.: GPT-4 Technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Barkan, O., Asher, Y., Eshel, A., Koenigstein, N.: Visual explanations via iterated integrated attributions. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00198"},{"key":"20_CR4","unstructured":"Belrose, N., et al.: Eliciting latent predictions from transformers with the tuned lens. arXiv preprint arXiv:2303.08112 (2023)"},{"key":"20_CR5","unstructured":"Beyer, L., et al.: PaliGemma: a versatile 3B VLM for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Bousselham, W., Boggust, A., Chaybouti, S., Strobelt, H., Kuehne, H.: LeGrad: an explainability method for vision transformers via feature formation sensitivity. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01891"},{"key":"20_CR7","unstructured":"Brunner, G., Liu, Y., Pascual, D., Richter, O., Ciaramita, M., Wattenhofer, R.: On identifiability in transformers. In: ICLR (2020)"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Bu\u00e7inca, Z., Malaya, M.B., Gajos, K.Z.: To trust or to think: cognitive forcing functions can reduce overreliance on ai in AI-assisted decision-making. Proceedings of the ACM on Human-Computer Interaction (2021)","DOI":"10.1145\/3449287"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Generic attention-model explainability for interpreting bi-modal and encoder-decoder transformers In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Clark, K., Khandelwal, U., Levy, O., Manning, C.D.: What does BERT look at? an analysis of BERT\u2019s attention. In: ACL (2019)","DOI":"10.18653\/v1\/W19-4828"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Ding, Y., Liu, Y., Luan, H., Sun, M.: Visualizing and understanding neural machine translation. In: ACL (2017)","DOI":"10.18653\/v1\/P17-1106"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Ferrando, J., G\u00e1llego, G.I., Alastruey, B., Escolano, C., Costa-juss\u00e0, M.R.: Towards opening the black box of neural machine translation: source and target interpretations of the transformer. In: ACL (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.599"},{"key":"20_CR14","unstructured":"Galassi, A., Lippi, M., Torroni, P.: Attention, please! a critical review of neural attention models in natural language processing. arXiv (2019)"},{"key":"20_CR15","unstructured":"Gandelsman, Y., Efros, A.A., Steinhardt, J.: Interpreting clip\u2019s image representation via text-based decomposition. In: ICLR (2024)"},{"key":"20_CR16","unstructured":"Gandelsman, Y., Efros, A.A., Steinhardt, J.: Interpreting the second-order effects of neurons in clip. In: ICLR (2025)"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Geva, M., Caciularu, A., Wang, K., Goldberg, Y.: Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.3"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"20_CR19","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. arXiv preprint arXiv:2310.14566 (2023)","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"20_CR20","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"20_CR21","unstructured":"Karpathy, A., Johnson, J., Fei-Fei, L.: Visualizing and understanding recurrent networks. In: Workshop ICLR (2016)"},{"key":"20_CR22","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: ICML, PMLR (2023)"},{"key":"20_CR23","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, PMLR (2022)"},{"key":"20_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, H., Ding, X., Wang, H., Li, X.: Token activation map to visually explain multimodal LLMs. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00012"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural Inf. Proces. Syst. (2024)","DOI":"10.52202\/075280-1516"},{"key":"20_CR27","unstructured":"nostalgebraist: interpreting GPT: the logit lens (2020) https:\/\/www.lesswrong.com\/posts\/AcKRB8wDpdaN6v6ru\/interpreting-gpt-the-logit-lens"},{"key":"20_CR28","unstructured":"Petsiuk, V., Das, A., Saenko, K.: RISE: randomized input sampling for explanation of black-box models. In: BMVC (2018)"},{"key":"20_CR29","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, PMLR (2021)"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Roslyn, S.A., A., N., R., V.S.: Enhancing accessibility for visually impaired users: a BLIP2-powered image description system in tamil. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS) (2024)","DOI":"10.1109\/ADICS58448.2024.10533565"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"20_CR32","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. IJCV (2020)","DOI":"10.1007\/s11263-019-01228-7"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Serrano, S., Smith, N.A.: Is attention interpretable?. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1282"},{"key":"20_CR34","unstructured":"SkunkworksAI: BakllaVA: vision-language model (2024). https:\/\/github.com\/SkunkworksAI\/BakLLaVA"},{"key":"20_CR35","unstructured":"Springenberg, J., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. In: ICLR (Workshop Track) (2015)"},{"key":"20_CR36","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: ICML, PMLR (2017)"},{"key":"20_CR37","unstructured":"Team, G.: Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"20_CR38","unstructured":"Templeton, A., et al.: Scaling monosemanticity: extracting interpretable features from claude 3 sonnet. Anthropic (2024)"},{"key":"20_CR39","unstructured":"Vaswani, A.: Attention is all you need. In: NIPS (2017)"},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Wiegreffe, S., Pinter, Y.: Attention is not not explanation. In: ACL (2019)","DOI":"10.18653\/v1\/D19-1002"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, B., et al.: Florence-2: advancing a unified representation for a variety of vision tasks. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Yang, B., He, L., Liu, K., Yan, Z.: VIAssist: adapting multi-modal large language models for users with visual impairments. arXiv preprint arXiv:2404.02508 (2024)","DOI":"10.1109\/FMSys62467.2024.00010"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: Explainability for large language models: a survey. ACM Trans. Intell. Syst. Technol. (2024)","DOI":"10.1145\/3639372"},{"key":"20_CR44","unstructured":"Zhao, Y., Zhang, Y., Xiang, R., Li, J., Li, H.: VIALM: a survey and benchmark of visually impaired assistance with large models. arXiv preprint arXiv:2402.01735 (2024)"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Zini, J.E., Awad, M.: On the explainability of natural language processing deep models. ACM Comput. Surv. (2022)","DOI":"10.1145\/3529755"}],"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\/978-3-032-37550-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:22:51Z","timestamp":1789233771000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37550-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375490","9783032375506"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37550-6_20","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"}}]}}