用归因分析压缩大模型提示词，省下七成令牌还更准
ProCut: LLM Prompt Compression via Attribution Estimation
- 通过语义切分与归因评估，识别并移除低效提示片段
- 工业场景下减少78%提示词长度，性能不降反升
- 无需训练、兼容现有框架，适合高并发提示优化
在大规模工业级大模型系统中，提示模板常因逐步加入任务指令、少样本示例和启发式规则而膨胀至数千令牌，导致维护困难、推理延迟高、服务成本上升。为解决此问题，我们提出基于归因估计的提示压缩框架ProCut，该方法无需训练、通用性强，通过将提示分割为语义单元，量化其对任务表现的影响，并剪枝低效部分。在五个公开基准数据集及真实工业提示上进行大量实验表明，ProCut可实现显著的提示压缩（生产环境减少78%令牌），同时保持甚至略微提升任务性能（相比其他方法最高提升62%）。我们进一步设计了由大模型驱动的归因估计算法，使压缩延迟降低超50%，且ProCut可无缝集成至现有提示优化框架，生成简洁高效提示。
原文摘要 · Abstract (English)
In large-scale industrial LLM systems, prompt templates often expand to thousands of tokens as teams iteratively incorporate sections such as task instructions, few-shot examples, and heuristic rules to enhance robustness and coverage. This expansion leads to bloated prompts that are difficult to maintain and incur significant inference latency and serving costs. To address this, we introduce Prompt Compression via Attribution Estimation (ProCut), a flexible, LLM-agnostic, training-free framework that compresses prompts through attribution analysis. ProCut segments prompt templates into semantically meaningful units, quantifies their impact on task performance, and prunes low-utility components. Through extensive experiments on five public benchmark datasets and real-world industrial prompts, we show that ProCut achieves substantial prompt size reductions (78% fewer tokens in production) while maintaining or even slightly improving task performance (up to 62% better than alternative methods). We further introduce an LLM-driven attribution estimator that reduces compression latency by over 50%, and demonstrate that ProCut integrates seamlessly with existing prompt-optimization frameworks to produce concise, high-performing prompts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。