{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T15:54:24Z","timestamp":1758124464048,"version":"3.40.5"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732461"},{"type":"electronic","value":"9783031732478"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73247-8_14","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T12:02:20Z","timestamp":1730376140000},"page":"232-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["BEAF: Observing BEfore-AFter Changes to\u00a0Evaluate Hallucination in\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0390-6567","authenticated-orcid":false,"given":"Moon","family":"Ye-Bin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9543-3770","authenticated-orcid":false,"given":"Nam","family":"Hyeon-Woo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2665-2388","authenticated-orcid":false,"given":"Wonseok","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0468-1571","authenticated-orcid":false,"given":"Tae-Hyun","family":"Oh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"14_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv (2023)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: Nocaps: novel object captioning at scale. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00904"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Bisk, Y., Zellers, R., Gao, J., Choi, Y., et\u00a0al.: PIQA: reasoning about physical commonsense in natural language. In: AAAI Conference on Artificial Intelligence (AAAI) (2020)","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"14_CR4","unstructured":"Chen, J., et al.: Minigpt-V2: large language model as a unified interface for vision-language multi-task learning. arXiv (2023)"},{"key":"14_CR5","unstructured":"Chen, K., Zhang, Z., Zeng, W., Zhang, R., Zhu, F., Zhao, R.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic. arXiv (2023)"},{"key":"14_CR6","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* chatgpt quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"14_CR7","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. arXiv (2021)"},{"key":"14_CR8","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"14_CR9","unstructured":"Deng, A., Chen, Z., Hooi, B.: Seeing is believing: mitigating hallucination in large vision-language models via clip-guided decoding. arXiv (2024)"},{"key":"14_CR10","unstructured":"Gao, P., et al.: Llama-adapter V2: parameter-efficient visual instruction model. arXiv (2023)"},{"key":"14_CR11","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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Gunjal, A., Yin, J., Bas, E.: Detecting and preventing hallucinations in large vision language models. In: AAAI Conference on Artificial Intelligence (AAAI) (2024)","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning. arXiv (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"14_CR14","unstructured":"Hu, H., Zhang, J., Zhao, M., Sun, Z.: Ciem: contrastive instruction evaluation method for better instruction tuning. arXiv (2023)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Hyun, L., Sung-Bin, K., Han, S., Yu, Y., Oh, T.H.: Smile: multimodal dataset for understanding laughter in video with language models. arXiv (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.73"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Leng, S., et al.: Mitigating object hallucinations in large vision-language models through visual contrastive decoding. arXiv (2023)","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"14_CR19","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. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision (ECCV) (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"14_CR21","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Mitigating hallucination in large multi-modal models via robust instruction tuning. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: A survey on hallucination in large vision-language models. arXiv (2024)","DOI":"10.54254\/2755-2721\/2024.17851"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. arXiv (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"14_CR24","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"14_CR25","unstructured":"Peng, Z., et al.: Kosmos-2: grounding multimodal large language models to the world. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"14_CR26","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2015)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2018)","DOI":"10.18653\/v1\/D18-1437"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Aligning large multimodal models with factually augmented RLHF. arXiv (2023)","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with fourier convolutions. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"14_CR31","unstructured":"Taori, R., et al.: Alpaca: a strong, replicable instruction-following model. Stanford Center for Research on Foundation Models, vol. 3, no. 6, p. 7 (2023)"},{"key":"14_CR32","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv (2023)"},{"key":"14_CR33","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv (2023)"},{"key":"14_CR34","unstructured":"Wang, J., et al.: An LLM-free multi-dimensional benchmark for MLLMs hallucination evaluation. arXiv (2023)"},{"key":"14_CR35","unstructured":"Wang, J., et al.: Evaluation and analysis of hallucination in large vision-language models. arXiv preprint arXiv:2308.15126 (2023)"},{"key":"14_CR36","unstructured":"Ye, Q., et al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv (2023)"},{"key":"14_CR37","unstructured":"Yin, S., et al.: Woodpecker: hallucination correction for multimodal large language models. arXiv (2023)"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. (TACL) (2014)","DOI":"10.1162\/tacl_a_00166"},{"key":"14_CR39","unstructured":"Zhai, B., et al.: Halle-switch: rethinking and controlling object existence hallucinations in large vision language models for detailed caption. arXiv preprint arXiv:2310.01779 (2023)"},{"key":"14_CR40","unstructured":"Zhang, R., et al.: LLaMA-adapter: efficient fine-tuning of language models with zero-init attention. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"14_CR41","unstructured":"Zhao, Y., et al.: Enhancing the spatial awareness capability of multi-modal large language model. arXiv (2023)"},{"key":"14_CR42","unstructured":"Zhou, Y., et al.: Analyzing and mitigating object hallucination in large vision-language models. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"14_CR43","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv (2023)"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Zhuang, J., Zeng, Y., Liu, W., Yuan, C., Chen, K.: A task is worth one word: learning with task prompts for high-quality versatile image inpainting. arXiv (2023)","DOI":"10.1007\/978-3-031-73636-0_12"}],"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\/978-3-031-73247-8_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T15:38:50Z","timestamp":1732981130000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73247-8_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732461","9783031732478"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73247-8_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}