{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:06Z","timestamp":1786120806305,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817738","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"2778-2789","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Modality-Agnostic Zeroth-Order LoRA Fine-Tuning for Black-Box Prompt Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8021-2815","authenticated-orcid":false,"given":"Xingchen","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5311-4871","authenticated-orcid":false,"given":"Jia","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2187-1641","authenticated-orcid":false,"given":"Tianxing","family":"Man","sequence":"additional","affiliation":[{"name":"Inner Mongolia University, Hohhot, Inner Mongolia, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9990-6433","authenticated-orcid":false,"given":"Wenkang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6049-1815","authenticated-orcid":false,"given":"Bin","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Anthropic. 2023. Claude AI Model Overview. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet"},{"key":"e_1_3_2_1_2_1","unstructured":"James Betker Gabriel Goh Li Jing Tim Brooks Jianfeng Wang Linjie Li Long Ouyang Juntang Zhuang Joyce Lee Yufei Guo et al. 2023. Improving image generation with better captions. Computer Science. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf V2 3 (2023) 8."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606725"},{"key":"e_1_3_2_1_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems V33 (2020) 1877-1901."},{"key":"e_1_3_2_1_5_1","volume-title":"Instructzero: Efficient instruction optimization for black-box large language models. arXiv preprint arXiv:2306.03082","author":"Chen Lichang","year":"2023","unstructured":"Lichang Chen, Jiuhai Chen, Tom Goldstein, Heng Huang, and Tianyi Zhou. 2023. Instructzero: Efficient instruction optimization for black-box large language models. arXiv preprint arXiv:2306.03082 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Black-box prompt optimization: Aligning large language models without model training. arXiv preprint arXiv:2311.04155","author":"Cheng Jiale","year":"2023","unstructured":"Jiale Cheng, Xiao Liu, Kehan Zheng, Pei Ke, Hongning Wang, Yuxiao Dong, Jie Tang, and Minlie Huang. 2023. Black-box prompt optimization: Aligning large language models without model training. arXiv preprint arXiv:2311.04155 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Black-box prompt learning for pre-trained language models. arXiv preprint arXiv:2201.08531","author":"Diao Shizhe","year":"2022","unstructured":"Shizhe Diao, Zhichao Huang, Ruijia Xu, Xuechun Li, Yong Lin, Xiao Zhou, and Tong Zhang. 2022. Black-box prompt learning for pre-trained language models. arXiv preprint arXiv:2201.08531 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"A systematic survey of prompt engineering on vision-language foundation models. arXiv preprint arXiv:2307.12980","author":"Gu Jindong","year":"2023","unstructured":"Jindong Gu, Zhen Han, Shuo Chen, Ahmad Beirami, Bailan He, Gengyuan Zhang, Ruotong Liao, Yao Qin, Volker Tresp, and Philip Torr. 2023. A systematic survey of prompt engineering on vision-language foundation models. arXiv preprint arXiv:2307.12980 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"V36","author":"Hao Yaru","year":"2023","unstructured":"Yaru Hao, Zewen Chi, Li Dong, and Furu Wei. 2023. Optimizing prompts for text-to-image generation. Advances in Neural Information Processing Systems, V36 (2023), 66923-66939."},{"key":"e_1_3_2_1_10_1","volume-title":"V28","author":"Hermann Karl Moritz","year":"2015","unstructured":"Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. 2015. Teaching machines to read and comprehend. Advances in neural information processing systems, V28 (2015)."},{"key":"e_1_3_2_1_11_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"V37","author":"Hu Wenyang","year":"2024","unstructured":"Wenyang Hu, Yao Shu, Zongmin Yu, Zhaoxuan Wu, Xiaoqiang Lin, Zhongxiang Dai, See-Kiong Ng, and Bryan Kian Hsiang Low. 2024. Localized zeroth-order prompt optimization. Advances in Neural Information Processing Systems, V37 (2024), 86309-86345."},{"key":"e_1_3_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Jacot Arthur","year":"2018","unstructured":"Arthur Jacot, Franck Gabriel, and Cl\u00e9ment Hongler. 2018. Neural Tangent Kernel: Convergence and Generalization in Neural Networks. In Advances in Neural Information Processing Systems, Vol. V31. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/5a4be1faeb0e2f3ce5f7f9c855d2e60b-Paper.pdf"},{"key":"e_1_3_2_1_14_1","volume-title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation. Advances in Neural Information Processing Systems, V36","author":"Kirstain Yuval","year":"2023","unstructured":"Yuval Kirstain, Adam Polyak, Uriel Singer, Shahbuland Matiana, Joe Penna, and Omer Levy. 2023. Pick-a-pic: An open dataset of user preferences for text-to-image generation. Advances in Neural Information Processing Systems, V36 (2023), 36652-36663."},{"key":"e_1_3_2_1_15_1","volume-title":"Myung-Seok Choi, Ryong Lee, and Sangtae Ahn.","author":"Lee Seunghun","year":"2024","unstructured":"Seunghun Lee, Jihoon Lee, Chan Ho Bae, Myung-Seok Choi, Ryong Lee, and Sangtae Ahn. 2024. Optimizing prompts using in-context few-shot learning for text-to-image generative models. IEEE Access, V12 (2024), 2660-2673."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_26"},{"key":"e_1_3_2_1_17_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_19_1","volume-title":"Zhengxiao Du, Zhilin Yang, and Jie Tang.","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Lam Tam, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2021. P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"Improving text-to-image consistency via automatic prompt optimization. arXiv preprint arXiv:2403.17804","author":"Oscar Ma","year":"2024","unstructured":"Oscar Ma nas, Pietro Astolfi, Melissa Hall, Candace Ross, Jack Urbanek, Adina Williams, Aishwarya Agrawal, Adriana Romero-Soriano, and Michal Drozdzal. 2024. Improving text-to-image consistency via automatic prompt optimization. arXiv preprint arXiv:2403.17804 (2024)."},{"key":"e_1_3_2_1_21_1","unstructured":"Tom\u00e1\u0161 Mikolov et al. 2012. Statistical language models based on neural networks. Presentation at Google Mountain View 2nd April V80 26 (2012)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"e_1_3_2_1_23_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. https:\/\/openai.com\/research\/gpt-4"},{"key":"e_1_3_2_1_24_1","unstructured":"OpenAI. 2025. GPT-Image-1 API Platform. https:\/\/platform.openai.com\/docs\/guides\/image-generation"},{"key":"e_1_3_2_1_25_1","volume-title":"A taxonomy of prompt modifiers for text-to-image generation. arXiv. arXiv preprint arXiv:2204.13988","author":"Oppenlaender Jonas","year":"2022","unstructured":"Jonas Oppenlaender. 2022. A taxonomy of prompt modifiers for text-to-image generation. arXiv. arXiv preprint arXiv:2204.13988 (2022)."},{"key":"e_1_3_2_1_26_1","volume-title":"A Taxonomy of Prompt Modifiers for Text-to-Image Generation. Behaviour & Information Technology","author":"Oppenlaender Jonas","year":"2023","unstructured":"Jonas Oppenlaender. 2023. A Taxonomy of Prompt Modifiers for Text-to-Image Generation. Behaviour & Information Technology (2023), 1-14."},{"key":"e_1_3_2_1_27_1","volume-title":"Ouyang","author":"Long","year":"2022","unstructured":"Long et al. Ouyang. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems (2022)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592000"},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_30_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog V1 8 (2019) 9."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_32_1","volume-title":"Grimm in wonderland: Prompt engineering with midjourney to illustrate fairytales. arXiv preprint arXiv:2302.08961","author":"Ruskov Martin","year":"2023","unstructured":"Martin Ruskov. 2023. Grimm in wonderland: Prompt engineering with midjourney to illustrate fairytales. arXiv preprint arXiv:2302.08961 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. Advances in Neural Information Processing Systems, V35 (2022), 36479-36494."},{"key":"e_1_3_2_1_34_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.119632"},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Sun Tianxiang","year":"2022","unstructured":"Tianxiang Sun, Yunfan Shao, Hong Qian, Xuanjing Huang, and Xipeng Qiu. 2022. Black-box tuning for language-model-as-a-service. In International Conference on Machine Learning. PMLR, 20841-20855."},{"key":"e_1_3_2_1_37_1","volume-title":"Private fine-tuning of large language models with zeroth-order optimization. arXiv preprint arXiv:2401.04343","author":"Tang Xinyu","year":"2024","unstructured":"Xinyu Tang, Ashwinee Panda, Milad Nasr, Saeed Mahloujifar, and Prateek Mittal. 2024. Private fine-tuning of large language models with zeroth-order optimization. arXiv preprint arXiv:2401.04343 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896","author":"Wang Zijie J","year":"2022","unstructured":"Zijie J Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen Horng Chau. 2022. Diffusiondb: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2210.14896 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341","author":"Wu Xiaoshi","year":"2023","unstructured":"Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023. Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.634"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657787"},{"key":"e_1_3_2_1_42_1","volume-title":"Prompt refinement with image pivot for text-to-image generation. arXiv preprint arXiv:2407.00247","author":"Zhan Jingtao","year":"2024","unstructured":"Jingtao Zhan, Qingyao Ai, Yiqun Liu, Yingwei Pan, Ting Yao, Jiaxin Mao, Shaoping Ma, and Tao Mei. 2024b. Prompt refinement with image pivot for text-to-image generation. arXiv preprint arXiv:2407.00247 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr","author":"Tianyi","year":"2020","unstructured":"Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr"},{"key":"e_1_3_2_1_44_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Zhou Yongchao","year":"2022","unstructured":"Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. 2022. Large language models are human-level prompt engineers. In The Eleventh International Conference on Learning Representations."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:11:15Z","timestamp":1786065075000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":44,"alternative-id":["10.1145\/3770855.3817738","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817738","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}