Retrieval-augmented generation (RAG) has emerged as a promising paradigm for enhancing large language models (LLMs) on multi-hop question answering (QA), which requires reasoning over evidence from multiple documents. Current multi-hop RAG methods generally focus on either query-side task decomposition or corpus-side knowledge graph construction. Despite their progress, these methods still struggle to achieve satisfactory performance on complex multi-hop QA tasks. To this end, we propose ConRAG, a consensus-driven multi-view RAG framework that effectively boosts LLMs on complex multi-hop QA. The core of ConRAG is to systematically optimize both the query and corpus sides and to leverage multi-view evidence (relation, entity, and text signals) for more accurate retrieval. Extensive experiments on three multi-hop QA benchmarks show that ConRAG consistently outperforms all baselines by a clear margin, e.g., up to +26.9% average performance gains over vanilla RAG, and enables Gemma-4-31B to achieve a new state-of-the-art record on the challenging MuSiQue benchmark.

翻译：检索增强生成（RAG）已成为增强大语言模型（LLM）在多跳问答任务中的一种有前景的范式，该任务需要对多个文档中的证据进行推理。当前多跳RAG方法通常侧重于查询侧的任务分解或语料侧的知识图谱构建。尽管取得了进展，这些方法在复杂的多跳问答任务上仍难以获得令人满意的性能。为此，我们提出ConRAG，一种共识驱动的多视角RAG框架，它能有效提升LLM在复杂多跳问答中的表现。ConRAG的核心在于系统性地优化查询侧和语料侧，并利用多视角证据（关系、实体和文本信号）来实现更精准的检索。在三个多跳问答基准上的大量实验表明，ConRAG以明显优势持续超越所有基线方法，例如，与原始RAG相比平均性能提升高达+26.9%，并使Gemma-4-31B在具有挑战性的MuSiQue基准上创下新的最优结果。