提出AMKOR框架，提升多源知识问答的推理准确率与鲁棒性。
Multi-granular Training Strategies for Robust Multi-hop Reasoning Over Noisy and Heterogeneous Knowledge Sources
- 动态融合参数化与检索知识，用概率束搜索探索推理路径
- 在HotpotQA等4个数据集上达到最新最优性能，显著提升准确率
- 适合需要处理噪声与异构知识的复杂多跳问答场景
多源多跳问答是自然语言处理中的挑战性任务，需动态整合异构知识源并进行多步推理。现有方法常面临误差累积、知识冲突处理不足和计算效率低的问题。本文提出自适应多源知识导向推理（AMKOR），一种基于大语言模型的生成式框架，可动态融合参数化与检索知识，并通过概率束搜索探索推理轨迹。AMKOR结合多粒度学习策略，同时优化局部推理步骤与全局答案准确率。在包括HotpotQA和MuSiQue在内的四个常用多跳问答数据集上的实验表明，AMKOR在推理准确率和鲁棒性上均显著优于基线方法，且具备良好可扩展性与对噪声知识的适应能力，有效兼顾推理质量与效率，为多源多跳问答建立新基准。
原文摘要 · Abstract (English)
Multi-source multi-hop question answering (QA) represents a challenging task in natural language processing due to the need for dynamic integration of heterogeneous knowledge sources and multi-step reasoning. Existing methods often suffer from cascading errors, insufficient handling of knowledge conflicts, and computational inefficiency. In this paper, we propose Adaptive Multi-source Knowledge-Oriented Reasoning (AMKOR), a generative framework that leverages large language models (LLMs) to dynamically fuse parametric and retrieved knowledge while exploring reasoning trajectories using probabilistic beam reasoning. AMKOR is further enhanced by a multi-granular learning strategy, optimizing both local reasoning steps and global answer accuracy. Experiments conducted on four widely-used multi-hop QA datasets, including HotpotQA and MuSiQue, demonstrate that AMKOR achieves state-of-the-art performance, significantly outperforming baseline methods on both reasoning accuracy and robustness. Additional analyses confirm its scalability, adaptability to noisy knowledge, and superior ability to handle complex multi-hop tasks. This work establishes a new benchmark for multi-source multi-hop QA by effectively combining reasoning quality and efficiency.
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。