Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression

• Published in: arXiv.org
• Main Authors: Ali, Muhammad Asif, Li, Zhengping, Yang, Shu, Cheng, Keyuan, Cao, Yang, Huang, Tianhao, Hu, Guimin, Lyu, Weimin, Hu, Lijie, Lu, Yu, Wang, Di
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 17.10.2024
• Subjects: Benchmarks; Compressing; Graphs; Large language models; Natural language processing; Readability

Large Language Models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we observe that there is a significant cost associated with exceedingly lengthy prompts. Existing attempts to compress lengthy...