EUVIMEDEUVIMED entdecken
Crossref

Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers

Xinyu Tang, Xiaolei Wang, Wayne Xin Zhao, Siyuan Lu, Yaliang Li, Ji-Rong Wen

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (24) · 25264-25272

DOI: 10.1609/aaai.v39i24.34713 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Xinyu Tang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic prompt optimization is an important approach to improving the performance of large language models (LLMs). Recent research demonstrates the potential of using LLMs as prompt optimizers, which can generate improved task prompts via iterative refinement. In this paper, we propose a novel perspective to investigate the design of LLM-based prompt optimizers, by drawing an analogy with gradient-based model optimizers. To connect these two approaches, we identify two pivotal factors in model parameter learning: update direction and update method. By systematically analyzing a rich set of improvement strategies on the two aspects, we further develop a capable Gradient-inspired LLM-based Prompt Optimizer called GPO. At each step, it first retrieves relevant prompts from the optimization trajectory as the update direction. Then, it utilizes the generation-based refinement strategy to perform the update, while controlling the edit distance through a cosine-based decay strategy. Extensive experiments demonstrate the effectiveness and efficiency of GPO. In particular, GPO brings an additional improvement of up to 56.8% on Big-Bench Hard and 62.6% on MMLU compared to baseline methods.

Zitieren

APA

Tang, X., Wang, X., Zhao, W. X., Lu, S., Li, Y., & Wen, J. (2025). Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers. Proceedings of the AAAI Conference on Artificial Intelligence, 39(24), 25264-25272. https://doi.org/10.1609/aaai.v39i24.34713

Vancouver

Tang X, Wang X, Zhao WX, Lu S, Li Y, Wen J. Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(24):25264-25272. doi:10.1609/aaai.v39i24.34713

BibTeX
@article{Tang2025,
  author = {Tang, Xinyu and Wang, Xiaolei and Zhao, Wayne Xin and Lu, Siyuan and Li, Yaliang and Wen, Ji-Rong},
  title = {Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {24},
  pages = {25264--25272},
  doi = {10.1609/aaai.v39i24.34713}
}
Kostenlos starten →