通过留一法识别关键句，实现高效精准的问答上下文压缩。
LooComp: Leverage Leave-One-Out Strategy to Encoder-only Transformer for Efficient Query-aware Context Compression
- 用留一法评估删减句子对线索丰富度的影响，筛选关键上下文。
- 在多个数据集上保持高准确率，压缩比优于主流方法。
- 轻量编码器架构适合部署，适合资源受限的问答系统。
高效的上下文压缩对于提升问答系统的准确性和可扩展性至关重要。在检索增强生成中，上下文需快速、紧凑且精确地传递，以保证线索充分性并降低大模型阅读成本。我们提出一种基于边际的查询驱动上下文剪枝框架，通过测量删除句子后线索丰富度的变化，识别回答问题的关键句子。模型采用复合排序损失训练，强制关键句子保持较大边际，非关键句则维持近中性。基于轻量级编码器仅变压器结构，该方法在保持强精确匹配与F1分数的同时，实现高吞吐推理和更低内存开销，显著优于主要基线。此外，本方法在不降低回答性能的前提下，实现了有效的压缩比，展现出作为检索增强任务轻量实用替代方案的巨大潜力。
原文摘要 · Abstract (English)
Efficient context compression is crucial for improving the accuracy and scalability of question answering. For the efficiency of Retrieval Augmented Generation, context should be delivered fast, compact, and precise to ensure clue sufficiency and budget-friendly LLM reader cost. We propose a margin-based framework for query-driven context pruning, which identifies sentences that are critical for answering a query by measuring changes in clue richness when they are omitted. The model is trained with a composite ranking loss that enforces large margins for critical sentences while keeping non-critical ones near neutral. Built on a lightweight encoder-only Transformer, our approach generally achieves strong exact-match and F1 scores with high-throughput inference and lower memory requirements than those of major baselines. In addition to efficiency, our method yields effective compression ratios without degrading answering performance, demonstrating its potential as a lightweight and practical alternative for retrieval-augmented tasks.
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。