Prompt’s Evolution for Language Model-Driven Data Generation
Source abstract
Abstract
In the era of data, data generation continues to grow day by day, posing new challenges for processing systems due to the dynamism of its volume, variety, and velocity. To process data in real time, stream processing systems (SPS) serve as the keystone of real-time data analytics systems. However, SPS must operate under strict quality of service (QoS) constraints, which require dynamic adaptation of their internal logic to sustain performance. In this work, we address the problem of automatic text data generation using large language models (LLMs) by employing an evolutionary approach to guide prompt learning. The process enables us to automatically discover prompts by applying a black-box approach to generate synthetic data from a reference dataset. This approach aims to enrich training datasets and enhance the generalization capabilities of AI-driven adaptive SPS models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning and Data Classification · Data Stream Mining Techniques · Time Series Analysis and Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Escuela de Informática y Telecomunicaciones, Facultad de Ingeniería y Ciencias, Universidad Diego Portales, Santiago 8581169, Chile
Department of Computer Engineering (DISCA), Universidad Polytecnica de Valencia, 46022 Valencia, Spain
Funding
Stic-Amsud ITERATION-D · Proyecto Enlace UDP 2025
References (37)
Show source-provided references
1. Big data preprocessing: Methods and prospects10.1186/s41044-016-0014-0 ↗
2. Hierarchical auto-scaling policies for data stream processing on heterogeneous resources10.1145/3597435 ↗
3. Self-adaptive processing graph with operator fission for elastic stream processing10.1016/j.jss.2016.06.010 ↗
4. Russo, G.R., D’Alessandro, E., Cardellini, V., and Presti, F.L. (2024, January 16–20). Towards a Multi-Armed Bandit Approach for Adaptive Load Balancing in Function-as-a-Service Systems. Proceedings of the 2024 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C), Aarhus, Denmark.10.1109/ACSOS-C63493.2024.00039 ↗
5. PA-SPS: A predictive adaptive approach for an elastic stream processing system10.1016/j.jpdc.2024.104940 ↗
6. Haidar, M.A., and Rezagholizadeh, M. (2019, January 28–31). Textkd-gan: Text generation using knowledge distillation and generative adversarial networks. Proceedings of the Advances in Artificial Intelligence: 32nd Canadian Conference on Artificial Intelligence, Canadian AI 2019, Kingston, ON, Canada.10.1007/978-3-030-18305-9_9 ↗
7. Zhang, Y., Gan, Z., Fan, K., Chen, Z., Henao, R., Shen, D., and Carin, L. (2017, January 6–11). Adversarial feature matching for text generation. Proceedings of the 34th International Conference on Machine Learning PMLR, Sydney, Australia.
8. Nie, W., Narodytska, N., and Patel, A. (May, January 30). Relgan: Relational generative adversarial networks for text generation. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
9. Yu, L., Zhang, W., Wang, J., and Yu, Y. (2017, January 4–9). Seqgan: Sequence generative adversarial nets with policy gradient. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10804 ↗
10. Xu, J., Ren, X., Lin, J., and Sun, X. (2018). Dp-gan: Diversity-promoting generative adversarial network for generating informative and diversified text. arXiv.
11. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems 27 (NIPS 2014), Montreal, QC, Canada.
12. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016, January 5–10). Improved techniques for training gans. Proceedings of the Advances in Neural Information Processing Systems 29 (NIPS 2016), Barcelona, Spain.
13. A review on metaheuristic-based synthetic data generation methods
14. Parameter setting in evolutionary algorithms10.1109/4235.771166 ↗
15. Shin, T., Razeghi, Y., Logan, R.L., Wallace, E., and Singh, S. (2020, January 16–20). AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.10.18653/v1/2020.emnlp-main.346 ↗
16. Li, X.L., and Liang, P. (2021, January 1–6). Prefix-Tuning: Optimizing Continuous Prompts for Generation. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Online.10.18653/v1/2021.acl-long.353 ↗
17. Pryzant, R., Iter, D., Li, J., Lee, Y.T., Zhu, C., and Zeng, M. (2023). Automatic prompt optimization with “gradient descent” and beam search. arXiv.10.18653/v1/2023.emnlp-main.494 ↗
18. Tong, Z., Ding, Z., and Wei, W. (2025, January 19–24). EvoPrompt: Evolving Prompts for Enhanced Zero-Shot Named Entity Recognition with Large Language Models. Proceedings of the 31st International Conference on Computational Linguistics, Abu Dhabi, United Arab Emirates.
19. Saletta, M., and Ferretti, C. (2024, January 14–18). Exploring the prompt space of large language models through evolutionary sampling. Proceedings of the Genetic and Evolutionary Computation Conference, Melbourne, VIC, Australia.10.1145/3638529.3654049 ↗
20. Tran, K.D., Bui, D.V., and Luong, N.H. (2023, January 5–6). Evolving Prompts for Synthetic Image Generation with Genetic Algorithm. Proceedings of the 2023 International Conference on Multimedia Analysis and Pattern Recognition (MAPR), Quy Nhon, Vietnam.10.1109/MAPR59823.2023.10288925 ↗
21. Wong, M., Ong, Y.S., Gupta, A., Bali, K.K., and Chen, C. (2023, January 5–6). Prompt Evolution for Generative AI: A Classifier-Guided Approach. Proceedings of the 2023 IEEE Conference on Artificial Intelligence (CAI), Santa Clara, CA, USA.10.1109/CAI54212.2023.00105 ↗
22. Pan, H., Lu, H., Gao, T., Shen, M., Zhang, W., Lin, Z., Cao, L., Xiao, J., Liu, Z., and Wen, M. (2023). Plum: Prompt Learning using Metaheuristics. arXiv.
23. Zhang, J., Huang, Z., Hu, M., Deng, Y., and Cai, S. (2024, January 6–10). EvoPrompting: Language Model Based Prompt Tuning for Few-Shot Learning. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore.
24. Evoprompting: Language models for code-level neural architecture search
25. Sécheresse, X., Guilbert-Ly, J.Y., and de Torcy, A.V. (2025). GAAPO: Genetic Algorithmic Applied to Prompt Optimization. arXiv.10.3389/frai.2025.1613007 ↗
26. Fernando, C., Banarse, D., Michalewski, H., Osindero, S., and Rocktäschel, T. (2023). Promptbreeder: Self-referential self-improvement via prompt evolution. arXiv.
27. Gao, Z., Gholami, A., Gu, B., Mao, Y., Ma, X., Zou, T., Yu, R., Lu, X., Chen, P., and Shi, H. (2025). Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications. arXiv.
28. Wladdimiro, D., Arantes, L., Sens, P., and Hidalgo, N. (2021, January 23–26). A multi-metric adaptive stream processing system. Proceedings of the 2021 IEEE 20th International Symposium on Network Computing and Applications (NCA), Boston, MA, USA.10.1109/NCA53618.2021.9685871 ↗
29. Wladdimiro, D., Pagliari, A., and Brum, R.C. (2025, January 23–26). Toward Stream Processing Efficiency Leveraging Cloud Burstable Instances. Proceedings of the 2025 IEEE International Conference on Cloud Engineering (IC2E), Rennes, France.10.1109/IC2E65552.2025.00039 ↗
30. Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., and Azhar, F. (2023). Llama: Open and efficient foundation language models. arXiv.
31. (2025, June 01). Ollama. Ollama: Run LLMs Locally. Available online: https://ollama.com/.
32. Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., and Artzi, Y. (2020, January 26–30). BERTScore: Evaluating Text Generation with BERT. Proceedings of the International Conference on Learning Representations, Addis Ababa, Ethiopia.
33. Shukla, A., Pandey, H.M., and Mehrotra, D. (2015, January 25–27). Comparative review of selection techniques in genetic algorithm. Proceedings of the 2015 International Conference on Futuristic Trends on Computational ANALYSIS and Knowledge Management (ABLAZE), Greater Noida, India.10.1109/ABLAZE.2015.7154916 ↗
34. Genetic algorithm performance with different selection strategies in solving TSP
35. Lamsal, R. (2025, June 01). Coronavirus (COVID-19) Tweets Dataset, IEEE Dataport. Available online: https://ieee-dataport.org/open-access/coronavirus-covid-19-tweets-dataset.
36. Niwattanakul, S., Singthongchai, J., Naenudorn, E., and Wanapu, S. (2013, January 13–15). Using of Jaccard coefficient for keywords similarity. Proceedings of the International Multiconference of Engineers and Computer Scientists, Hong Kong.
37. Estimating the selectivity of tf-idf based cosine similarity predicates10.1145/1328854.1328855 ↗