Credible Plan-Driven RAG Method for Multi-Hop Question Answering
This addresses a key bottleneck in complex QA systems for applications requiring reliable multi-step reasoning, though it appears incremental as it builds on existing RAG frameworks.
The paper tackles the problem of error propagation and reasoning drift in multi-hop question answering with retrieval-augmented generation (RAG), proposing PAR-RAG, which outperforms state-of-the-art methods on various QA benchmarks.
Multi-hop question answering (QA) presents significant challenges for retrieval-augmented generation (RAG), particularly in decomposing complex queries into reliable reasoning paths and managing error propagation. Existing RAG methods often suffer from deviations in reasoning paths and cumulative errors in intermediate steps, reducing the fidelity of the final answer. To address these limitations, we propose PAR-RAG (Plan-then-Act-and-Review RAG), a novel framework inspired by the PDCA (Plan-Do-Check-Act) cycle, to enhance both the accuracy and factual consistency in multi-hop question answering. Specifically, PAR-RAG selects exemplars matched by the semantic complexity of the current question to guide complexity-aware top-down planning, resulting in more precise and coherent multi-step reasoning trajectories. This design mitigates reasoning drift and reduces the risk of suboptimal path convergence, a common issue in existing RAG approaches. Furthermore, a dual-verification mechanism evaluates and corrects intermediate errors, ensuring that the reasoning process remains factually grounded. Experimental results on various QA benchmarks demonstrate that PAR-RAG outperforms existing state-of-the-art methods, validating its effectiveness in both performance and reasoning robustness.