500xCompressor: Generalized Prompt Compression for Large Language Models

TL;DR

This paper introduces 500xCompressor, a novel prompt compression method that significantly reduces prompt size with minimal parameter increase, maintaining most of the LLM's capabilities across various datasets.

Contribution

The paper presents 500xCompressor, a universal prompt compression technique that achieves high compression ratios without fine-tuning, addressing limitations of existing methods.

Findings

Achieves compression ratios from 6x to 480x

Retains 62.26-72.89% of LLM capabilities

Utilizes K V values for better information preservation

Abstract

Prompt compression is crucial for enhancing inference speed, reducing costs, and improving user experience. However, current methods face challenges such as low compression ratios and potential data leakage during evaluation. To address these issues, we propose 500xCompressor, a method that compresses extensive natural language contexts into a minimum of one single special token. The 500xCompressor introduces approximately 0.3% additional parameters and achieves compression ratios ranging from 6x to 480x. It is designed to compress any text, answer various types of questions, and could be utilized by the original large language model (LLM) without requiring fine-tuning. Initially, 500xCompressor was pretrained on the Arxiv Corpus, followed by fine-tuning on the ArxivQA dataset, and subsequently evaluated on strictly unseen and classical question answering (QA) datasets. The results demonstrate that the LLM retained 62.26-72.89% of its capabilities compared to using non-compressed prompts. This study also shows that not all the compressed tokens are equally utilized and that K V values have significant advantages over embeddings in preserving information at high compression ratios. The highly compressive nature of natural language prompts, even for fine-grained complex information, suggests promising potential for future applications and further research into developing a new LLM language.