{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:54:36Z","timestamp":1763790876729,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533459","type":"print"},{"value":"9789819533466","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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\/978-981-95-3346-6_6","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:50:17Z","timestamp":1763790617000},"page":"75-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bi-directional Semantic Alignment for\u00a0Large Vision Language Model Training via\u00a0Echo-Former"],"prefix":"10.1007","author":[{"given":"Ye","family":"Wang","sequence":"first","affiliation":[]},{"given":"Qingwen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zejun","family":"Li","sequence":"additional","affiliation":[]},{"given":"Siyuan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shijie","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Zhongyu","family":"Wei","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"6_CR1","unstructured":"GPT-4v(ision) system card (2023). https:\/\/api.semanticscholar.org\/CorpusID:263218031"},{"key":"6_CR2","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"6_CR3","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"6_CR4","unstructured":"Bai, Y., et\u00a0al.: Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)"},{"key":"6_CR5","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: ShareGPT4v: improving large multi-modal models with better captions. arXiv preprint arXiv:2311.12793 (2023)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"6_CR7","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR8","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models (2024)"},{"key":"6_CR9","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Gunjal, A., Yin, J., Bas, E.: Detecting and preventing hallucinations in large vision language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 18135\u201318143 (2024)","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Gurari, D., et al.: Vizwiz grand challenge: answering visual questions from blind people. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133617 (2018)","DOI":"10.1109\/CVPR.2018.00380"},{"key":"6_CR12","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"6_CR13","unstructured":"Hu, H., Zhang, J., Zhao, M., Sun, Z.: Ciem: contrastive instruction evaluation method for better instruction tuning. arXiv preprint arXiv:2309.02301 (2023)"},{"key":"6_CR14","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. arXiv preprint arXiv:2311.17911 (2023)","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"6_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","DOI":"10.1109\/CVPR.2019.00686"},{"issue":"12","key":"6_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023)","journal-title":"ACM Comput. Surv."},{"key":"6_CR17","unstructured":"Jiang, A.Q., et al.: Mistral 7b (2023)"},{"key":"6_CR18","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: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"6_CR19","unstructured":"Li, L., et\u00a0al.: M3IT: a large-scale dataset towards multi-modal multilingual instruction tuning. arXiv preprint arXiv:2306.04387 (2023)"},{"key":"6_CR20","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":"6_CR21","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Aligning large multi-modal model with robust instruction tuning. arXiv preprint arXiv:2306.14565 (2023)"},{"key":"6_CR22","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":"6_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":"6_CR24","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al.: MMBench: is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"6_CR26","unstructured":"OpenAI: ChatGPT (August 3 version) (2023). https:\/\/chat.openai.com\/chat"},{"key":"6_CR27","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27730\u201327744 (2022)"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"6_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. arXiv preprint arXiv:1809.02156 (2018)","DOI":"10.18653\/v1\/D18-1437"},{"key":"6_CR31","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"6_CR32","unstructured":"Stiennon, N., et al.: Learning to summarize with human feedback. In: Advances in Neural Information Processing Systems, vol. 33, pp. 3008\u20133021 (2020)"},{"key":"6_CR33","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":"6_CR34","doi-asserted-by":"crossref","unstructured":"Thrush, T., et al.: Winoground: probing vision and language models for visio-linguistic compositionality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"6_CR35","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"6_CR36","unstructured":"Wang, J., et al.: An LLM-free multi-dimensional benchmark for MLLMs hallucination evaluation. arXiv preprint arXiv:2311.07397 (2023)"},{"key":"6_CR37","unstructured":"Wang, W., et\u00a0al.: CogVLM: visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)"},{"key":"6_CR38","unstructured":"Wu, T., Zhu, B., Zhang, R., Wen, Z., Ramchandran, K., Jiao, J.: Pairwise proximal policy optimization: harnessing relative feedback for LLM alignment. arXiv preprint arXiv:2310.00212 (2023)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Yu, T., et\u00a0al.: RLHF-V: towards trustworthy MLLMs via behavior alignment from fine-grained correctional human feedback. arXiv preprint arXiv:2312.00849 (2023)","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"6_CR40","unstructured":"Yuan, Y., Yue, Y., Zhu, R., Fan, T., Yan, L.: What\u2019s behind PPO\u2019s collapse in long-CoT? Value optimization holds the secret. arXiv preprint arXiv:2503.01491 (2025)"},{"key":"6_CR41","unstructured":"Zhang, Y., et\u00a0al.: Siren\u2019s song in the AI ocean: a survey on hallucination in large language models. arXiv preprint arXiv:2309.01219 (2023)"},{"key":"6_CR42","unstructured":"Zheng, R., et\u00a0al.: Secrets of RLHF in large language models part i: PPO. arXiv preprint arXiv:2307.04964 (2023)"},{"key":"6_CR43","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3346-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:50:35Z","timestamp":1763790635000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3346-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533459","9789819533466"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3346-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}