{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:40:48Z","timestamp":1778258448789,"version":"3.51.4"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730092","type":"print"},{"value":"9783031730108","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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\/978-3-031-73010-8_8","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T13:12:28Z","timestamp":1731157948000},"page":"125-140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Paying More Attention to\u00a0Image: A Training-Free Method for\u00a0Alleviating Hallucination in\u00a0LVLMs"],"prefix":"10.1007","author":[{"given":"Shi","family":"Liu","sequence":"first","affiliation":[]},{"given":"Kecheng","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"8_CR1","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning (2022)"},{"key":"8_CR2","unstructured":"Anisha, G., Yin, J., Bas, E.: Detecting and preventing hallucinations in large vision language models (2023)"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Azaria, A., Mitchell, T.: The internal state of an LLM knows when its lying (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.68"},{"key":"8_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. arXiv, Computation and Language (2020)"},{"key":"8_CR5","unstructured":"Burns, C., Ye, H., Klein, D., Steinhardt, J.: Discovering latent knowledge in language models without supervision (2022)"},{"key":"8_CR6","unstructured":"Chen, K., et al.: Shikra: unleashing multimodal LLM\u2019s referential dialogue magic (2023)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks (2023)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"8_CR8","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"8_CR9","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. arXiv preprint arXiv:2309.16588 (2023)"},{"key":"8_CR10","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"8_CR11","unstructured":"Han, Y., et al.: ChartLlama: a multimodal LLM for chart understanding and generation (2023)"},{"key":"8_CR12","unstructured":"Hu, H., Zhang, J., Zhao, M., Sun, Z.: CIEM: contrastive instruction evaluation method for better instruction tuning (2023)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Q., et al.: Opera: alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation (2023)","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Kai, J., Zhang, T., Hu, H., Lin, Z.: SH2: self-highlighted hesitation helps you decode more truthfully (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.260"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: LISA: reasoning segmentation via large language model (2023)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Leng, S., et al.: Mitigating object hallucinations in large vision-language models through visual contrastive decoding (2023)","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"8_CR17","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models (2023)"},{"key":"8_CR18","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_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. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Monkey: image resolution and text label are important things for large multi-modal models (2023)","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"8_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: The Twelfth International Conference on Learning Representations (2023)"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: A survey on hallucination in large vision-language models (2024)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"8_CR23","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_CR24","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y., Madison, M., Research, M.: Visual instruction tuning (2023)"},{"key":"8_CR25","doi-asserted-by":"publisher","unstructured":"Mishra, S., Khashabi, D., Baral, C., Hajishirzi, H.: Cross-task generalization via natural language crowdsourcing instructions. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.244","DOI":"10.18653\/v1\/2022.acl-long.244"},{"key":"8_CR26","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback (2022)"},{"key":"8_CR27","unstructured":"Peng, B., Li, C., He, P., Galley, M., Gao, J.: Instruction tuning with GPT-4 (2023)"},{"key":"8_CR28","doi-asserted-by":"publisher","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018). https:\/\/doi.org\/10.18653\/v1\/d18-1437","DOI":"10.18653\/v1\/d18-1437"},{"key":"8_CR29","unstructured":"Sanchez, G., Fan, H., Spangher, A., Levi, E., Ammanamanchi, P.S., Biderman, S.: Stay on topic with classifier-free guidance. arXiv preprint arXiv:2306.17806 (2023)"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Sun, Z., et\u00a0al.: Aligning large multimodal models with factually augmented RLHF. arXiv preprint arXiv:2309.14525 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"8_CR31","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023)"},{"key":"8_CR32","unstructured":"Turner, A., Thiergart, L., Udell, D., Leech, G., Mini, U., MacDiarmid, M.: Activation addition: steering language models without optimization. arXiv preprint arXiv:2308.10248 (2023)"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Label words are anchors: an information flow perspective for understanding in-context learning. arXiv preprint arXiv:2305.14160 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.609"},{"key":"8_CR34","unstructured":"Wei, F., Zhang, X., Zhang, A., Zhang, B., Chu, X.: Lenna: language enhanced reasoning detection assistant (2023)"},{"key":"8_CR35","unstructured":"Wei, J., et al.: Finetuned language models are zero-shot learners. Learning (2021)"},{"key":"8_CR36","unstructured":"Xiao, G., Tian, Y., Chen, B., Han, S., Lewis, M.: Efficient streaming language models with attention sinks (2023)"},{"key":"8_CR37","unstructured":"Ye, Q., et al.: mPLUG-Owl: modularization empowers large language models with multimodality (2023)"},{"key":"8_CR38","unstructured":"Yin, S., et al.: Woodpecker: hallucination correction for multimodal large language models (2023)"},{"key":"8_CR39","unstructured":"You, H., et al.: Ferret: refer and ground anything anywhere at any granularity (2023)"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Qian, S., Peng, B., Liu, S., Jia, J.: Prompt highlighter: interactive control for multi-modal LLMs. arXiv preprint arXiv:2312.04302 (2023)","DOI":"10.1109\/CVPR52733.2024.01255"},{"key":"8_CR41","unstructured":"Zhou, Y., et al.: Analyzing and mitigating object hallucination in large vision-language models (2023)"},{"key":"8_CR42","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models (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\/978-3-031-73010-8_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:24:12Z","timestamp":1733019852000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73010-8_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031730092","9783031730108"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73010-8_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 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"}}]}}