通过记忆增强推理，提升跨多跳问答的准确率。
Omne-R1: Learning to Reason with Memory for Multi-hop Question Answering
- 采用多阶段训练，融合强化学习与监督微调。
- 在复杂三跳以上问题上表现显著提升。
- 适用于跨领域知识图谱，通用性强。
本文提出Omne-R1，一种通过整合先进推理模型来增强无模式知识图谱上多跳问答能力的新方法。该方法采用多阶段训练流程，包括两个强化学习阶段和一个监督微调阶段。为解决可用知识图谱和问答数据有限的问题，我们构建了领域无关的知识图谱，并自动生成问答对。实验结果表明，在回答多跳问题方面取得显著改进，尤其在更复杂的三跳及以上问题上表现突出。所提出的训练框架在多种知识领域中展现出强大的泛化能力。
原文摘要 · Abstract (English)
This paper introduces Omne-R1, a novel approach designed to enhance multi-hop question answering capabilities on schema-free knowledge graphs by integrating advanced reasoning models. Our method employs a multi-stage training workflow, including two reinforcement learning phases and one supervised fine-tuning phase. We address the challenge of limited suitable knowledge graphs and QA data by constructing domain-independent knowledge graphs and auto-generating QA pairs. Experimental results show significant improvements in answering multi-hop questions, with notable performance gains on more complex 3+ hop questions. Our proposed training framework demonstrates strong generalization abilities across diverse knowledge domains.
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。