Mapping text to multiplex graph: Prompt compression as Lévy walk-guided graph pruning

2026-05-04

Knowledge-Based Systems

AI Summary

为解决文本压缩中信息分布问题，提出RAGP方法，通过Lévy Walk指导的多重图剪枝来高效识别非冗余节点，实验表明其性能优于现有方法。

Abstract

Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is often spread across multiple locations and connected through both local syntactic dependencies and global semantic relations. Such relational structure is naturally represented as a graph, where tokens or sentences become nodes and their dependencies become edges. To this end, we propose RAGP, which formulates prompt compression as Redundancy-Aware Graph Pruning on a multiplex graph that jointly models fine-grained attention-based dependencies and coarse-grained semantic relations. To efficiently identify non-redundant nodes in this heterogeneous structure (dense local subgraphs and sparse global connections), we employ Levy walks whose heavy-tailed step distribution naturally balances local exploitation with global exploration. Experiments on LongBench show that RAGP achieves an average score of 49.3 under a 4x compression ratio, outperforming existing LLM-based compression methods, such as LongLLMLingua, which attains 48.8 at a 3x compression ratio. Besides, RAGP also surpasses state-of-the-art vision-based text compression paradigms on multiple tasks. The code is available at https://anonymous.4open.science/r/RAGP-B0CB.

Problem

• prompt compression
• multiplex graph
• semantic relations
• syntactic dependencies

Innovation

• multiplex graph
• Lévy walk
• redundancy-aware pruning
• attention-based dependencies
• semantic relations