受大脑振荡启发，提升多跳问答的推理准确性和鲁棒性
THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA
- 模仿脑内Theta-Gamma振荡，分层规划与局部检索协同
- 在多个基准上显著降低错误累积，提升答案准确率
- 适用于不同模型架构，适合研究多跳推理机制者
多跳问答需要从多个上下文中检索并整合证据。尽管研究进展迅速，多跳推理仍受限于两个长期问题：注意力衰减，即随着推理链增长，模型对主问题的关注度下降；以及错误累积，即错误在各步骤间传播并最终导致失败。受Theta-Gamma分层振荡启发——该机制将全局规划与局部检索解耦，实现跨步骤的高效注意力传递，并具备验证与修复机制，可中断错误路径的累积——我们提出THOR，一种类脑的Theta-Gamma分层振荡推理框架。在多跳问答基准上的大量对比实验与专项验证实验表明，THOR在提升答案准确率和鲁棒性的同时，有效缓解了上述限制，展现出对不同骨干模型的泛化能力。
原文摘要 · Abstract (English)
Multi-hop question answering requires retrieving and integrating evidence from multiple contexts. Despite the rapid progress of current research, multi-hop reasoning remains constrained by two persistent limitations: attention decay, where the model's focus on main question degrades as the reasoning chain grows, and error accumulation, where mistakes propagate across hops and compounds into final failure. Inspired by Theta-Gamma hierarchical oscillation which decouples global planning from local retrieval, enabling efficient attention transfer between hops and a verification and repair mechanism that interrupts the accumulation of errors in the wrong paths, we present THOR, a brain-inspired Theta-Gamma hierarchical oscillatory reasoning framework. Extensive comparative experiments and specific validation experiments on multi-hop QA benchmarks demonstrate that THOR improves answer accuracy and robustness while mitigating limitations, showcasing its generalization across different backbones.
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。