{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T13:44:36Z","timestamp":1767015876850,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031756221"},{"type":"electronic","value":"9783031756238"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-75623-8_28","type":"book-chapter","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T19:16:41Z","timestamp":1735845401000},"page":"348-360","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Bayesian Approach for\u00a0Prompt Optimization in\u00a0LLMs"],"prefix":"10.1007","author":[{"given":"Antonio","family":"Sabbatella","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Ponti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilaria","family":"Giordani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Archetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"28_CR1","unstructured":"Anonymous. Large language models to enhance bayesian optimization. In: Submitted to The Twelfth International Conference on Learning Representations (2023)"},{"key":"28_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24494-1","volume-title":"Bayesian Optimization and Data Science","author":"F Archetti","year":"2019","unstructured":"Archetti, F., Candelieri, A.: Bayesian Optimization and Data Science. Springer International Publishing, Berlin, Germany (2019)"},{"key":"28_CR3","first-page":"21524","volume":"33","author":"M Balandat","year":"2020","unstructured":"Balandat, M., et al.: BoTorch: a framework for efficient monte-carlo bayesian optimization. Adv. Neural. Inf. Process. Syst. 33, 21524\u201321538 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR5","unstructured":"Burns, C., et al.: Weak-to-strong generalization: eliciting strong capabilities with weak supervision. arXiv preprint arXiv:2312.09390 (2023)"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Chai, Y., Wang, S., Sun, Y., Tian, H., Wu, H., Wang, H.: Clip-tuning: towards derivative-free prompt learning with a mixture of rewards. arXiv preprint arXiv:2210.12050 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.8"},{"key":"28_CR7","unstructured":"Chen, L., Chen, J., Goldstein, T., Huang, H., Zhou, T.: InstructZero: efficient instruction optimization for black-box large language models. arXiv preprint arXiv:2306.03082 (2023)"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"de Curt\u00f2 i D\u00edaz, J., et al.: LLM-informed multi-armed bandit strategies for non-stationary environments (2023)","DOI":"10.3390\/electronics12132814"},{"key":"28_CR9","unstructured":"Diao, S., et al.: Black-box prompt learning for pre-trained language models. arXiv preprint arXiv:2201.08531 (2022)"},{"key":"28_CR10","unstructured":"Gao, Y., Fei, N., Liu, G., Lu, Z., Xiang, T.: Contrastive prototype learning with augmented embeddings for few-shot learning. In: Uncertainty in Artificial Intelligence, pp. 140\u2013150 (2021)"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Garnett, R.: Bayesian Optimization. Cambridge University Press (2023)","DOI":"10.1017\/9781108348973"},{"key":"28_CR12","unstructured":"Guo, Q., et al.: Connecting large language models with evolutionary algorithms yields powerful prompt optimizers. arXiv preprint arXiv:2309.08532 (2023)"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Honovich, O., Shaham, U., Bowman, S. R., Levy, O.: Instruction induction: from few examples to natural language task descriptions. arXiv preprint arXiv:2205.10782 (2022)","DOI":"10.18653\/v1\/2023.acl-long.108"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"28_CR15","unstructured":"Li, J., et al.: BayesPrompt: prompting large-scale pre-trained language models on few-shot inference via debiased domain abstraction. arXiv preprint arXiv:2401.14166 (2024)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Lin, B.: Reinforcement learning and bandits for speech and language processing: tutorial, review and outlook. Expert Systems with Applications, p. 122254 (2023)","DOI":"10.1016\/j.eswa.2023.122254"},{"key":"28_CR17","unstructured":"Lin, X., et al.: Use your INSTINCT: instruction optimization using neural bandits coupled with transformers. arXiv preprint arXiv:2310.02905 (2023)"},{"key":"28_CR18","unstructured":"Ma, R., et al.: Are large language models good prompt optimizers?. arXiv preprint arXiv:2402.02101 (2024)"},{"key":"28_CR19","first-page":"34505","volume":"35","author":"N Maus","year":"2022","unstructured":"Maus, N., Jones, H., Moore, J., Kusner, M.J., Bradshaw, J., Gardner, J.: Local latent space Bayesian optimization over structured inputs. Adv. Neural. Inf. Process. Syst. 35, 34505\u201334518 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR20","unstructured":"Maus, N., Chao, P., Wong, E., Gardner, J.R.: Black box adversarial prompting for foundation models. In: The Second Workshop on New Frontiers in Adversarial Machine Learning (2023)"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Prasad, A., Hase, P., Zhou, X., Bansal, M.: Grips: gradient-free, edit-based instruction search for prompting large language models. arXiv preprint arXiv:2203.07281 (2022)","DOI":"10.18653\/v1\/2023.eacl-main.277"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Pryzant, R., Iter, D., Li, J., Lee, Y. T., Zhu, C., Zeng, M.: Automatic prompt optimization with gradient descent and beam search. arXiv preprint arXiv:2305.03495 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.494"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Reynolds, L., McDonell, K.: Prompt programming for large language models: beyond the few-shot paradigm. In: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1\u20137 (2021)","DOI":"10.1145\/3411763.3451760"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Sabbatella, A., Ponti, A., Candelieri, A., Giordani, I., Archetti, F.: A Bayesian approach for prompt optimization in pre-trained language models. arXiv preprint arXiv:2312.00471 (2023)","DOI":"10.3390\/math12060929"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Sun, T., He, Z., Qian, H., Zhou, Y., Huang, X.J., Qiu, X.: BBTv2: towards a gradient-free future with large language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3916\u20133930 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.259"},{"key":"28_CR26","unstructured":"Sun, T., Shao, Y., Qian, H., Huang, X., Qiu, X.: Black-box tuning for language-model-as-a-service. In: International Conference on Machine Learning, pp. 20841\u201320855 (2022)"},{"key":"28_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"28_CR28","unstructured":"Wang, X., et al.: Promptagent: strategic planning with language models enables expert-level prompt optimization. arXiv preprint arXiv:2310.16427 (2023)"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S. R. GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"28_CR30","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"28_CR31","unstructured":"Xie, S. M., Raghunathan, A., Liang, P., Ma, T.: An explanation of in-context learning as implicit Bayesian inference. arXiv preprint arXiv:2111.02080 (2021)"},{"key":"28_CR32","unstructured":"Yang, C., et al.: Large language models as optimizers. arXiv preprint arXiv:2309.03409 (2023)"},{"key":"28_CR33","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601, 2023"},{"key":"28_CR34","unstructured":"Zhang, M. R., Desai, N., Bae, J., Lorraine, J., Ba, J.: Using large language models for hyperparameter optimization. arXiv e-prints, arXiv-2312 (2023)"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, H., Wan, X., Vuli\u0107, I., Korhonen, A.: Survival of the most influential prompts: efficient black-box prompt search via clustering and pruning. arXiv preprint arXiv:2310.12774 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.870"},{"key":"28_CR36","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","Learning and Intelligent Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-75623-8_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T09:09:34Z","timestamp":1741684174000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-75623-8_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031756221","9783031756238"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-75623-8_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LION","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Learning and Intelligent Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ischia Island","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":"9 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 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":"lion2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.lion18.unina.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}