让复杂问答更高效：通过迭代压缩关键证据，提升多跳推理准确率。
IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering
- 基于多跳推理设计迭代压缩机制，逐步聚焦核心证据。
- 在三个数据集上同时提升准确率与效率，最高减少40%的输入token。
- 无需训练，适合需要高精度推理的开放域问答场景。
多跳问答需跨多个证据段进行复杂推理，常导致检索增强生成系统因上下文过长且噪声多而效率与准确率下降。现有提示压缩方法多针对单轮查询，难以捕捉推理步骤间的依赖关系。本文提出IterCOMP，一种统一、无需训练的提示压缩框架，将多跳推理融入迭代压缩循环。该方法将文档分解为证据片段，评估问题可回答性，并生成针对性追问，逐轮整合关键证据，生成紧凑且以推理为导向的提示。在MusiQue、2WikiMultiHopQA和HotpotQA上的实验表明，IterCOMP在保持更低令牌预算的同时，显著提升精确匹配和F1得分，优于现有基线，且在推理复杂度增加时仍具鲁棒性。
原文摘要 · Abstract (English)
Multi-hop question answering requires complex reasoning across multiple evidence segments, which often overwhelms retrieval-augmented generation systems with lengthy and noisy contexts, thereby undermining both efficiency and accuracy. While existing prompt compression methods attempt to address this issue, they are typically designed for single-turn queries and fail to capture interdependent reasoning steps. We propose IterCOMP, a unified, training-free prompt compression framework that incorporates multi-hop reasoning within an iterative compression loop. IterCOMP decomposes documents into evidence segments, evaluates question answerability, and generates targeted follow-up questions to iteratively integrate essential evidence, producing a compact, reasoning-oriented prompt. Experiments on MusiQue, 2WikiMultiHopQA, and HotpotQA demonstrate that IterCOMP achieves substantial improvements in Exact Match and F1 scores while reducing the token budget, outperforming existing baselines and exhibiting robustness as reasoning complexity increases.
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。