只问缺失信息，让大模型高效推理多跳问题
Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG
- 先检索奠基，再只针对信息缺口生成追问
- 准确率达60.63%，推理成本仅为其他方法的1/3
- 适合需要精准、低成本多步推理的应用场景
多跳问答对检索增强生成（RAG）仍是挑战，因现有方法或在多轮检索中传播错误，或过度生成推理步骤，增加开销却不提升准确率。我们提出基于规划的接地增量推理框架GDP-RAG，通过三个设计选择：(1) 先进行初步检索以支撑规划，(2) 使用条件式规划提示，仅请求缺失信息，(3) 采用骨架式推理轨迹，将每个子查询与一个承载前期检索证据的Thought配对并传递至最终答案。GDP-RAG聚焦于未解决的信息缺口，生成简洁可靠的推理路径。在HotpotQA、2WikiMultiHopQA和MuSiQue上的实验表明，GDP-RAG在所有对比系统中达到最高准确率（60.63%），同时保持每轮成本0.51，比PAR-RAG（0.65）低22%，比KnowTrace（1.57）低68%，无任何方法能同时实现更高准确率和更低开销。
原文摘要 · Abstract (English)
Multi-hop question answering remains challenging for Retrieval-Augmented Generation (RAG) because existing approaches either propagate errors across iterative retrieval rounds or over-generate reasoning steps, increasing cost without improving accuracy. We propose Grounded Delta Planning RAG (GDP-RAG), a plan-based framework that targets only the information delta based on three simple design choices: (1) preliminary retrieval to ground planning before execution, (2) a gap-conditioned planning prompt that asks only for missing information, and (3) a skeletal trajectory that pairs each subquery with a Thought capturing evidence from preliminary retrieval and carrying it through to the final answer. GDP-RAG focuses computation on unresolved gaps, yielding concise, reliable reasoning trajectories. Extensive experiments on HotpotQA, 2WikiMultiHopQA, and MuSiQue show that GDP-RAG achieves the highest accuracy (60.63%) among all compared systems while maintaining a cost-of-pass of 0.51, 22% lower than PAR-RAG (0.65) and 68% lower than KnowTrace (1.57), with no method achieving both higher accuracy and lower cost.
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。