Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2510.18043 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915565840367616 |
|---|---|
| author | Choi, Joong Ho Zhao, Jiayang Shah, Jeel Sonawane, Ritvika Singh, Vedant Appalla, Avani Flanagan, Will Condessa, Filipe |
| author_facet | Choi, Joong Ho Zhao, Jiayang Shah, Jeel Sonawane, Ritvika Singh, Vedant Appalla, Avani Flanagan, Will Condessa, Filipe |
| contents | Large Language Models (LLMs) deliver powerful reasoning and generation capabilities but incur substantial run-time costs when operating in agentic workflows that chain together lengthy prompts and process rich data streams. We introduce CompactPrompt, an end-to-end pipeline that merges hard prompt compression with lightweight file-level data compression. CompactPrompt first prunes low-information tokens from prompts using self-information scoring and dependency-based phrase grouping. In parallel, it applies n-gram abbreviation to recurrent textual patterns in attached documents and uniform quantization to numerical columns, yielding compact yet semantically faithful representations. Integrated into standard LLM agents, CompactPrompt reduces total token usage and inference cost by up to 60% on benchmark dataset like TAT-QA and FinQA, while preserving output quality (Results in less than 5% accuracy drop for Claude-3.5-Sonnet, and GPT-4.1-Mini) CompactPrompt helps visualize real-time compression decisions and quantify cost-performance trade-offs, laying the groundwork for leaner generative AI pipelines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_18043 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CompactPrompt: A Unified Pipeline for Prompt Data Compression in LLM Workflows Choi, Joong Ho Zhao, Jiayang Shah, Jeel Sonawane, Ritvika Singh, Vedant Appalla, Avani Flanagan, Will Condessa, Filipe Artificial Intelligence Large Language Models (LLMs) deliver powerful reasoning and generation capabilities but incur substantial run-time costs when operating in agentic workflows that chain together lengthy prompts and process rich data streams. We introduce CompactPrompt, an end-to-end pipeline that merges hard prompt compression with lightweight file-level data compression. CompactPrompt first prunes low-information tokens from prompts using self-information scoring and dependency-based phrase grouping. In parallel, it applies n-gram abbreviation to recurrent textual patterns in attached documents and uniform quantization to numerical columns, yielding compact yet semantically faithful representations. Integrated into standard LLM agents, CompactPrompt reduces total token usage and inference cost by up to 60% on benchmark dataset like TAT-QA and FinQA, while preserving output quality (Results in less than 5% accuracy drop for Claude-3.5-Sonnet, and GPT-4.1-Mini) CompactPrompt helps visualize real-time compression decisions and quantify cost-performance trade-offs, laying the groundwork for leaner generative AI pipelines. |
| title | CompactPrompt: A Unified Pipeline for Prompt Data Compression in LLM Workflows |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.18043 |