{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T02:06:35Z","timestamp":1780106795804,"version":"3.54.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819794331","type":"print"},{"value":"9789819794348","type":"electronic"}],"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\/978-981-97-9434-8_23","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"295-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["PROMPTIST: Automated Prompt Optimization for\u00a0Text-to-Image Synthesis"],"prefix":"10.1007","author":[{"given":"WeiJie","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuejie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"23_CR1","unstructured":"Amatriain, X.: Prompt design and engineering: introduction and advanced methods (2024)"},{"key":"23_CR2","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., Hajishirzi, H.: Self-rag: learning to retrieve, generate, and critique through self-reflection (2023)"},{"key":"23_CR3","unstructured":"Betker, J., et\u00a0al.: Improving image generation with better captions. Comput. Sci. 2(3), \u00a08 (2023). https:\/\/cdnopenai.com\/papers\/dall-e-3.pdf"},{"key":"23_CR4","doi-asserted-by":"publisher","unstructured":"Cao, T., Wang, C., Liu, B., Wu, Z., Zhu, J., Huang, J.: BeautifulPrompt: towards automatic prompt engineering for text-to-image synthesis. In: Wang, M., Zitouni, I. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track. pp. 1\u201311. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-industry.1, https:\/\/aclanthology.org\/2023.emnlp-industry.1","DOI":"10.18653\/v1\/2023.emnlp-industry.1"},{"key":"23_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: Scene-based text-to-image generation with human priors (2022)","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"23_CR7","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey (2024)"},{"key":"23_CR8","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 (2022)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"23_CR9","unstructured":"Huang, J., Ping, W., Xu, P., Shoeybi, M., Chang, K.C.C., Catanzaro, B.: Raven: in-context learning with retrieval-augmented encoder-decoder language models (2024)"},{"key":"23_CR10","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation (2023)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Lampinen, A.K., et al.: Can language models learn from explanations in context? (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.38"},{"key":"23_CR12","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks (2021)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection (2018)","DOI":"10.1109\/ICCV.2017.324"},{"key":"23_CR14","unstructured":"OpenAI: chat GPT (2024). https:\/\/openai.com\/chatgpt. Accessed 11 Apr 2024"},{"key":"23_CR15","doi-asserted-by":"publisher","unstructured":"Oppenlaender, J.: A taxonomy of prompt modifiers for text-to-image generation. Beh. Inf. Technol. 1\u201314 (2023). https:\/\/doi.org\/10.1080\/0144929x.2023.2286532","DOI":"10.1080\/0144929x.2023.2286532"},{"key":"23_CR16","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback (2022)"},{"key":"23_CR17","unstructured":"Podell, D., et al.: SDXL: Improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"23_CR18","unstructured":"Qin, J., et al.: DiffusionGPT: LLM-driven text-to-image generation system (2024)"},{"key":"23_CR19","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022)"},{"key":"23_CR20","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International conference on machine learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"23_CR22","unstructured":"Rosenman, S., Lal, V., Howard, P.: Neuroprompts: An adaptive framework to optimize prompts for text-to-image generation (2024)"},{"key":"23_CR23","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models (2022)"},{"key":"23_CR24","doi-asserted-by":"publisher","unstructured":"Wang, Z.J., Montoya, E., Munechika, D., Yang, H., Hoover, B., Chau, D.H.: DiffusionDB: a large-scale prompt gallery dataset for text-to-image generative models. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, Canada, pp. 893\u2013911. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.51, https:\/\/aclanthology.org\/2023.acl-long.51","DOI":"10.18653\/v1\/2023.acl-long.51"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Wu, X., Sun, K., Zhu, F., Zhao, R., Li, H.: Human preference score: better aligning text-to-image models with human preference (2023)","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: Boxdiff: text-to-image synthesis with training-free box-constrained diffusion (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"23_CR27","unstructured":"Yasunaga, M., et al.: Retrieval-augmented multimodal language modeling (2023)"},{"key":"23_CR28","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation (2022)"},{"key":"23_CR29","unstructured":"Zhang, Z., Sabuncu, M.R.: Generalized cross entropy loss for training deep neural networks with noisy labels (2018)"},{"key":"23_CR30","unstructured":"Zhou, Y., et al.: Large language models are human-level prompt engineers (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\/978-981-97-9434-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:38:01Z","timestamp":1730385481000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9434-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794331","9789819794348"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9434-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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":"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":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}