{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:06:18Z","timestamp":1789538778167,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376237","type":"print"},{"value":"9783032376244","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\/978-3-032-37624-4_25","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:51:09Z","timestamp":1789537869000},"page":"407-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HERO: Enhancing Multimodal Faithfulness via\u00a0Dynamic Entropy-Aware Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Xiongfeng","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun-Yu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Fang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"25_CR3","unstructured":"Bai, Z., et al.: Hallucination of multimodal large language models: a survey. arXiv preprint arXiv:2404.18930 (2024)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., Qin, L., Zhang, J., Chen, Z., Xu, X., Che, W.: M3CoT: a novel benchmark for multi-domain multi-step multi-modal chain-of-thought. arXiv preprint arXiv:2405.16473 (2024)","DOI":"10.18653\/v1\/2024.acl-long.446"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites. arXiv preprint arXiv:2404.16821 (2024)","DOI":"10.1007\/s11432-024-4231-5"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: InternVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"25_CR7","doi-asserted-by":"crossref","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 American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Dong, Y., et al.: Insight-V: exploring long-chain visual reasoning with multimodal large language models. arXiv preprint arXiv:2411.14432 (2024)","DOI":"10.1109\/CVPR52734.2025.00847"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2025)","DOI":"10.52202\/085713-4899"},{"key":"25_CR10","unstructured":"Fu, S., Yang, Q., Li, Y.M., Wei, X., Xie, X., Zheng, W.S.: LOVE-R1: advancing long video understanding with an adaptive zoom-in mechanism via multi-step reasoning. arXiv preprint arXiv:2509.24786 (2025)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Fu, Y., Xie, R., Sun, X., Kang, Z., Li, X.: Mitigating hallucination in multimodal large language model via hallucination-targeted direct preference optimization. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 16563\u201316577 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.850"},{"key":"25_CR12","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14375\u201314385 (2024)","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"He, J., et al.: Cracking the code of hallucination in LVLMs with vision-aware head divergence. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3488\u20133501 (2025)","DOI":"10.18653\/v1\/2025.acl-long.175"},{"key":"25_CR14","unstructured":"He, P., Gao, J., Chen, W.: DeBERTaV3: improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing. arXiv preprint arXiv:2111.09543 (2021)"},{"key":"25_CR15","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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13418\u201313427 (2024)","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"25_CR16","unstructured":"Huang, W., et al.: Vision-R1: incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749 (2025)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Kaul, P., et al.: THRONE: an object-based hallucination benchmark for the free-form generations of large vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27228\u201327238 (2024)","DOI":"10.1109\/CVPR52733.2024.02571"},{"key":"25_CR18","doi-asserted-by":"publisher","first-page":"22199","DOI":"10.52202\/068431-1613","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. Adv. Neural. Inf. Process. Syst. 35, 22199\u201322213 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Leng, S., et al.: Mitigating object hallucinations in large vision-language models through visual contrastive decoding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13872\u201313882 (2024)","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"25_CR20","unstructured":"Li, B., et al.: LLaVA-next: stronger LLMs supercharge multimodal capabilities in the wild, May 2024. https:\/\/llava-vl.github.io\/blog\/2024-05-10-llava-next-stronger-llms\/. Accessed 29 June 2026"},{"key":"25_CR21","unstructured":"Li, F., et al.: LLaVA-NeXT-Interleave: tackling multi-image, video, and 3D in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)"},{"key":"25_CR22","unstructured":"Li, J., Zhang, J., Jie, Z., Ma, L., Li, G.: Mitigating hallucination for large vision language model by inter-modality correlation calibration decoding. arXiv preprint arXiv:2501.01926 (2025)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Li, P., Wang, G., Gu, W., Li, X., Liu, X., Zhang, Y.: An attack detection mechanism in smart contracts based on deep learning and feature fusion. Inf. Sci. 722, 122645 (2025)","DOI":"10.1016\/j.ins.2025.122645"},{"key":"25_CR24","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":"25_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y.M., et al.: IRG-MotionLLM: interleaving motion generation, assessment and refinement for text-to-motion generation. arXiv preprint arXiv:2512.10730 (2025)","DOI":"10.1007\/978-3-032-37550-6_3"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Lin, K.Y., Wang, H., Ren, W., Han, K.: Panoptic captioning: an equivalence bridge for image and text. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-2631"},{"key":"25_CR27","unstructured":"Liu, C., et al.: More thinking, less seeing? Assessing amplified hallucination in multimodal reasoning models. arXiv preprint arXiv:2505.21523 (2025)"},{"key":"25_CR28","unstructured":"Liu, H., et al.: A survey on hallucination in large vision-language models. arXiv preprint arXiv:2402.00253 (2024)"},{"key":"25_CR29","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)","DOI":"10.52202\/075280-1516"},{"key":"25_CR31","unstructured":"Liu, S., Ye, H., Xing, L., Zou, J.: In-context vectors: making in context learning more effective and controllable through latent space steering. arXiv preprint arXiv:2311.06668 (2023)"},{"key":"25_CR32","unstructured":"Liu, S., Ye, H., Zou, J.: Reducing hallucinations in large vision-language models via latent space steering. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"25_CR33","doi-asserted-by":"publisher","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol 15064, pp. 216\u2013233. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72658-3_13","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"25_CR34","unstructured":"Lu, P., et al.: MathVista: evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)"},{"key":"25_CR35","unstructured":"Luo, R., et al.: URSA: understanding and verifying chain-of-thought reasoning in multimodal mathematics. arXiv preprint arXiv:2501.04686 (2025)"},{"key":"25_CR36","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural. Inf. Process. Syst. 36, 53728\u201353741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR37","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"25_CR38","unstructured":"Shao, Z., et\u00a0al.: DeepSeekMath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Shi, W., et al.: Math-LLaVA: bootstrapping mathematical reasoning for multimodal large language models (2024). https:\/\/arxiv.org\/abs\/2406.17294","DOI":"10.18653\/v1\/2024.findings-emnlp.268"},{"key":"25_CR40","doi-asserted-by":"publisher","first-page":"74952","DOI":"10.52202\/075280-3275","volume":"36","author":"M Turpin","year":"2023","unstructured":"Turpin, M., Michael, J., Perez, E., Bowman, S.: Language models don\u2019t always say what they think: unfaithful explanations in chain-of-thought prompting. Adv. Neural. Inf. Process. Syst. 36, 74952\u201374965 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR41","unstructured":"Wang, C., et al.: MLLM can see? Dynamic correction decoding for hallucination mitigation. arXiv preprint arXiv:2410.11779 (2024)"},{"key":"25_CR42","unstructured":"Wang, J., et\u00a0al.: AMBER: an LLM-free multi-dimensional benchmark for MLLMs hallucination evaluation. arXiv preprint arXiv:2311.07397 (2023)"},{"key":"25_CR43","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models (2023). https:\/\/arxiv.org\/abs\/2201.11903"},{"key":"25_CR44","unstructured":"Wu, Z., et\u00a0al.: DeepSeek-VL2: mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)"},{"key":"25_CR45","unstructured":"Xiang, K., et al.: AtomThink: a slow thinking framework for multimodal mathematical reasoning (2024). https:\/\/arxiv.org\/abs\/2411.11930"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Xie, Y., Li, G., Xu, X., Kan, M.Y.: V-DPO: mitigating hallucination in large vision language models via vision-guided direct preference optimization. arXiv preprint arXiv:2411.02712 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.775"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Xu, G., Jin, P., Li, H., Song, Y., Sun, L., Yuan, L.: LLaVA-CoT: let vision language models reason step-by-step (2024). https:\/\/arxiv.org\/abs\/2411.10440","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"25_CR48","unstructured":"Xu, H., et\u00a0al.: mPLUG-2: a modularized multi-modal foundation model across text, image and video. In: International Conference on Machine Learning, pp. 38728\u201338748. PMLR (2023)"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: R1-Onevision: Advancing generalized multimodal reasoning through cross-modal formalization. arXiv preprint arXiv:2503.10615 (2025)","DOI":"10.1109\/ICCV51701.2025.00229"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Yang, Z., Luo, X., Han, D., Xu, Y., Li, D.: Mitigating hallucinations in large vision-language models via DPO: on-policy data hold the key. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10610\u201310620 (2025)","DOI":"10.1109\/CVPR52734.2025.00992"},{"issue":"12","key":"25_CR51","doi-asserted-by":"publisher","first-page":"220105","DOI":"10.1007\/s11432-024-4251-x","volume":"67","author":"S Yin","year":"2024","unstructured":"Yin, S., et al.: Woodpecker: hallucination correction for multimodal large language models. Sci. China Inf. Sci. 67(12), 220105 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: RLHF-V: towards trustworthy MLLMs via behavior alignment from fine-grained correctional human feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13807\u201313816 (2024)","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"25_CR54","unstructured":"Zhang, X., et al.: GPT-4V(ision) as a generalist evaluator for vision-language tasks. arXiv preprint arXiv:2311.01361 (2023)"},{"issue":"9","key":"25_CR55","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1093\/comjnl\/bxaf027","volume":"68","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Wang, G., Li, P., Gu, W., Chen, H.: FRACE: front-running attack classification on Ethereum using ensemble learning. Comput. J. 68(9), 1137\u20131149 (2025)","journal-title":"Comput. J."},{"key":"25_CR56","unstructured":"Zhang, Z., Zhang, A., Li, M., Zhao, H., Karypis, G., Smola, A.: Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923 (2023)"},{"key":"25_CR57","unstructured":"Zhao, Z., Wang, B., Ouyang, L., Dong, X., Wang, J., He, C.: Beyond hallucinations: enhancing LVLMs through hallucination-aware direct preference optimization (2023)"},{"key":"25_CR58","unstructured":"Zhao, Z., Wang, B., Ouyang, L., Dong, X., Wang, J., He, C.: Beyond hallucinations: enhancing LVLMs through hallucination-aware direct preference optimization. arXiv preprint arXiv:2311.16839 (2023)"},{"key":"25_CR59","unstructured":"Zheng, H., Xu, T., Sun, H., Pu, S., Chen, R., Sun, L.: Thinking before looking: improving multimodal LLM reasoning via mitigating visual hallucination. arXiv preprint arXiv:2411.12591 (2024)"}],"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\/978-3-032-37624-4_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:51:37Z","timestamp":1789537897000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37624-4_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376237","9783032376244"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37624-4_25","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":"17 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"}}]}}