Proceedings

PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models

Zheng Zhang, Jinyi Li, Yihuai Lan, Xiang Wang, Hao Wang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Demo Track. Pages 11127-11131.

https://doi.org/10.24963/ijcai.2025/1277

Keywords

  • Natural Language Processing: NLP: Language models
  • Natural Language Processing: NLP: Applications

Abstract

Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, prompt compression reduces prompt length while maintaining LLM response quality. To support rapid implementation and standardization, we present the Prompt Compression Toolkit (PCToolkit), a unified plug-and-play framework for LLM prompt compression. PCToolkit integrates state-of-the-art compression algorithms, benchmark datasets, and evaluation metrics, enabling systematic performance analysis. Its modular architecture simplifies customization, offering portable interfaces for seamless incorporation of new datasets, metrics, and compression methods. Our code is available at https://github.com/3DAgentWorld/Toolkit-for-Prompt-Compression. Our demo is at https://huggingface.co/spaces/CjangCjengh/Prompt-Compression-Toolbox.

Zheng Zhang, Jinyi Li, Yihuai Lan, Xiang Wang, and Hao Wang. 2025. PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language Models. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 11127–11131. https://doi.org/10.24963/ijcai.2025/1277
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards