用AI代理分步检索，精准高效解答多跳问题
PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
- 设计三类AI代理：分析问题、筛选相关文本、补充遗漏信息
- 在四个基准测试中，检索准确率显著优于现有方法
- 适合需要高精度推理的复杂问答场景
检索在多跳问答中至关重要，需整合多段证据回答复杂问题。我们提出PRISM，一种基于大语言模型的结构化智能体检索框架，通过循环协作实现高精度与高召回率。该框架将检索拆分为三个专精代理：问题分析器将复杂问题分解为子问题，选择器聚焦于每个子问题的相关上下文（强调精度），添加器补充缺失证据（强调召回）。选择器与添加器的迭代交互生成紧凑而全面的证据集，避免错误传播和冗余信息堆积。实验在四个挑战性多跳问答数据集（HotpotQA、2WikiMultiHopQA、MuSiQue、MultiHopRAG）上表明，该方法持续超越强基线，使下游问答模型在依赖更少无关信息的情况下，达到超过全上下文答案的准确率。
原文摘要 · Abstract (English)
Retrieval plays a central role in multi-hop question answering (QA), where answering complex questions requires gathering multiple pieces of evidence. We propose PRISM, an agentic retrieval framework that leverages large language models (LLMs) in a structured loop to retrieve relevant evidence with high precision and recall. PRISM decomposes retrieval into three specialized agents: a Question Analyzer that breaks complex queries into sub-questions, a Selector that identifies the most relevant context for each sub-question (focusing on precision), and an Adder that brings in any missing evidence (focusing on recall). The iterative interaction between the Selector and Adder produces a compact yet comprehensive evidence set, avoiding both brittle error propagation and noisy context accumulation. It achieves higher retrieval accuracy while filtering out distracting content, enabling downstream QA models to surpass full-context answer accuracy while relying on significantly less irrelevant information. Experiments on four challenging multi-hop QA benchmarks, including HotpotQA, 2WikiMultiHopQA, MuSiQue, and MultiHopRAG, demonstrate that our approach consistently outperforms strong baselines.
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。