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

arXiv:2404.00489v1 Announce Type: cross
Abstract: 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 prompts lead to sub-standard results in terms of readability and interpretability of the compressed prompt, with a detrimental impact on prompt utility. To address this, we propose PROMPT-SAW: Prompt compresSion via Relation AWare …

abstract arxiv compression cost cs.ai cs.cl cs.lg graphs inference language language models language processing large language large language models llm llms multiple natural natural language natural language processing observe processing prompt prompting prompts results standard tasks textual tool type