{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:47:06Z","timestamp":1778082426996,"version":"3.51.4"},"publisher-location":"Cham","reference-count":70,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734137","type":"print"},{"value":"9783031734144","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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\/978-3-031-73414-4_22","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:02:54Z","timestamp":1729789374000},"page":"382-398","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Strengthening Multimodal Large Language Model with\u00a0Bootstrapped Preference Optimization"],"prefix":"10.1007","author":[{"given":"Renjie","family":"Pi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyang","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jipeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runtao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"22_CR1","unstructured":"Bai, J., et al.: Qwen-vl: a versatile vision-language model for understanding, localization, text reading, and beyond (2023)"},{"key":"22_CR2","unstructured":"Bai, Y., et\u00a0al.: Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)"},{"key":"22_CR3","unstructured":"Bai, Y., et\u00a0al.: Constitutional AI: Harmlessness from AI feedback. arXiv preprint arXiv:2212.08073 (2022)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Bradley, R.A., Terry, M.E.: Rank analysis of incomplete block designs: I. The method of paired comparisons. Biometrika 39(3\/4), 324\u2013345 (1952)","DOI":"10.1093\/biomet\/39.3-4.324"},{"key":"22_CR5","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Sharegpt4v: improving large multi-modal models with better captions (2023)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"22_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations (2020)"},{"key":"22_CR8","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":"22_CR9","unstructured":"Choshen, L., Fox, L., Aizenbud, Z., Abend, O.: On the weaknesses of reinforcement learning for neural machine translation. arXiv preprint arXiv:1907.01752 (2019)"},{"key":"22_CR10","unstructured":"Chowdhery, A., et\u00a0al.: Palm: scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)"},{"key":"22_CR11","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"22_CR12","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Diao, S., et al.: Lmflow: an extensible toolkit for finetuning and inference of large foundation models. arXiv preprint arXiv:2306.12420 (2023)","DOI":"10.18653\/v1\/2024.naacl-demo.12"},{"key":"22_CR14","unstructured":"Ding, X., Han, J., Xu, H., Zhang, W., Li, X.: Hilm-d: towards high-resolution understanding in multimodal large language models for autonomous driving. arXiv preprint arXiv:2309.05186 (2023)"},{"key":"22_CR15","unstructured":"Ding, X., Han, J., Xu, H., Zhang, W., Li, X.: Hilm-d: towards high-resolution understanding in multimodal large language models for autonomous driving (2023)"},{"key":"22_CR16","unstructured":"Dong, H., et al.: Raft: reward ranked finetuning for generative foundation model alignment (2023)"},{"key":"22_CR17","unstructured":"Douglas, R., Draguns, A., Gaven\u010diak, T.: Mitigating the problem of strong priors in LMS with context extrapolation (2024)"},{"key":"22_CR18","unstructured":"Gao, J., et al.: Self-guided noise-free data generation for efficient zero-shot learning (2023)"},{"key":"22_CR19","unstructured":"Gao, J., et al.: G-llava: solving geometric problem with multi-modal large language model (2023)"},{"key":"22_CR20","unstructured":"Gao, P., et al.: Llama-adapter v2: parameter-efficient visual instruction model (2023)"},{"key":"22_CR21","unstructured":"Geng, X., Liu, H.: Openllama: an open reproduction of llama (2023). https:\/\/github.com\/openlm-research\/open_llama"},{"key":"22_CR22","unstructured":"Glaese, A., et\u00a0al.: Improving alignment of dialogue agents via targeted human judgements. arXiv preprint arXiv:2209.14375 (2022)"},{"key":"22_CR23","unstructured":"Google. Gemini: a family of highly capable multimodal models (2023). https:\/\/storage.googleapis.com\/deepmind-media\/gemini\/gemini_1_report.pdf"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Han, T., et al.: The instinctive bias: spurious images lead to hallucination in MLLMs (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.904"},{"key":"22_CR25","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020)"},{"key":"22_CR26","unstructured":"Hoffmann, J., et\u00a0al.: Training compute-optimal large language models. arXiv preprint arXiv:2203.15556 (2022)"},{"key":"22_CR27","unstructured":"Leike, J., Krueger, D., Everitt, T., Martic, M., Maini, V., Legg, S.: Scalable agent alignment via reward modeling: a research direction. arXiv preprint arXiv:1811.07871 (2018)"},{"key":"22_CR28","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":"22_CR29","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning (2023)"},{"key":"22_CR30","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day (2023)"},{"key":"22_CR31","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":"22_CR32","unstructured":"Li, L., et al.: Silkie: preference distillation for large visual language models (2023)"},{"key":"22_CR33","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 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"22_CR34","unstructured":"Lin, Y., et\u00a0al.: Speciality vs generality: an empirical study on catastrophic forgetting in fine-tuning foundation models. arXiv preprint arXiv:2309.06256 (2023)"},{"key":"22_CR35","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Mitigating hallucination in large multi-modal models via robust instruction tuning (2023)"},{"key":"22_CR36","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"22_CR37","unstructured":"Liu, X., Zhu, Y., Lan, Y., Yang, C., Qiao, Y.: Query-relevant images jailbreak large multi-modal models (2023)"},{"key":"22_CR38","unstructured":"Meng, Y., Huang, J., Zhang, Y., Han, J.: Generating training data with language models: towards zero-shot language understanding. arXiv preprint arXiv:2202.04538 (2022)"},{"key":"22_CR39","unstructured":"Meng, Y., Michalski, M., Huang, J., Zhang, Y., Abdelzaher, T., Han, J.: Tuning language models as training data generators for augmentation-enhanced few-shot learning (2023)"},{"key":"22_CR40","unstructured":"Nakano, R., et\u00a0al.: Webgpt: browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332 (2021)"},{"key":"22_CR41","unstructured":"OpenAI. Gpt-4 technical report (2023)"},{"key":"22_CR42","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Pi, R., et al.: Detgpt: detect what you need via reasoning (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.876"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Pi, R., et al.: MLLM-protector: ensuring MLLM\u2019s safety without hurting performance (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.895"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Pi, R., Yao, L., Gao, J., Zhang, J., Zhang, T.: Perceptiongpt: effectively fusing visual perception into LLM (2023)","DOI":"10.1109\/CVPR52733.2024.02561"},{"key":"22_CR46","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C.D., Finn, C.: Direct preference optimization: Your language model is secretly a reward model (2023)"},{"key":"22_CR47","unstructured":"Ramamurthy, R., et al.: Is reinforcement learning (not) for natural language processing?: Benchmarks, baselines, and building blocks for natural language policy optimization. arXiv preprint arXiv:2210.01241 (2022)"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning (2019)","DOI":"10.18653\/v1\/D18-1437"},{"key":"22_CR49","unstructured":"Scao, T.L., et\u00a0al.: Bloom: a 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)"},{"key":"22_CR50","unstructured":"Scheurer, J., et al.: Training language models with language feedback at scale. arXiv preprint arXiv:2303.16755 (2023)"},{"key":"22_CR51","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017)"},{"key":"22_CR52","unstructured":"Smith, S., et\u00a0al.: Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model. arXiv preprint arXiv:2201.11990 (2022)"},{"key":"22_CR53","unstructured":"Stiennon, N., et al.: Learning to summarize with human feedback. Adv. Neural. Inf. Process. Syst. 33, 3008\u20133021 (2020)"},{"key":"22_CR54","unstructured":"Su, Y., Lan, T., Li, H., Xu, J., Wang, Y., Cai, D.: Pandagpt: one model to instruction-follow them all (2023)"},{"key":"22_CR55","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Aligning large multimodal models with factually augmented RLHF (2023)","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"22_CR56","unstructured":"Taori, R., et al.: Stanford alpaca: an instruction-following llama model (2023). https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"22_CR57","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Arithmetic control of LLMs for diverse user preferences: directional preference alignment with multi-objective rewards. arXiv preprint arXiv:2402.18571 (2024)","DOI":"10.18653\/v1\/2024.acl-long.468"},{"key":"22_CR59","unstructured":"Wu, J., et al.: Recursively summarizing books with human feedback. arXiv preprint arXiv:2109.10862 (2021)"},{"key":"22_CR60","unstructured":"Xiong, W., Dong, H., Ye, C., Zhong, H., Jiang, N., Zhang, T.: Gibbs sampling from human feedback: a provable kl-constrained framework for RLHF. arXiv preprint arXiv:2312.11456 (2023)"},{"key":"22_CR61","doi-asserted-by":"crossref","unstructured":"Ye, J., et al.: Zerogen: efficient zero-shot learning via dataset generation. In: Empirical Methods in Natural Language Processing (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.801"},{"key":"22_CR62","unstructured":"Yin, S., et al.: Woodpecker: hallucination correction for multimodal large language models (2023)"},{"key":"22_CR63","unstructured":"Yu, L., et al.: Metamath: bootstrap your own mathematical questions for large language models (2023)"},{"key":"22_CR64","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: RLHF-V: Towards trustworthy MLLMs via behavior alignment from fine-grained correctional human feedback (2023)","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"22_CR65","unstructured":"Yu, W., et al.: Mm-vet: evaluating large multimodal models for integrated capabilities (2023)"},{"key":"22_CR66","unstructured":"Yuan, Z., Yuan, H., Tan, C., Wang, W., Huang, S., Huang, F.: RRHF: rank responses to align language models with human feedback without tears. arXiv preprint arXiv:2304.05302 (2023)"},{"key":"22_CR67","doi-asserted-by":"publisher","DOI":"10.1017\/9781009093057","author":"T Zhang","year":"2023","unstructured":"Zhang, T.: Mathematical Analysis of Machine Learning Algorithms. Cambridge University Press (2023). https:\/\/doi.org\/10.1017\/9781009093057","journal-title":"Cambridge University Press"},{"key":"22_CR68","unstructured":"Zhang, Y., et al.: Llavar: enhanced visual instruction tuning for text-rich image understanding (2024)"},{"key":"22_CR69","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models (2023)"},{"key":"22_CR70","unstructured":"Ziegler, D.M., et al.: Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593 (2019)"}],"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\/978-3-031-73414-4_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T06:51:53Z","timestamp":1732949513000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73414-4_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031734137","9783031734144"],"references-count":70,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73414-4_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 October 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"}}]}}