arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.01783cs.AI
收藏

GAM-RAG:基于增益的记忆用于演化检索的检索增强生成

GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation

Fudan University(复旦大学)

Yifan Wang, Mingxuan Jiang, Zhihao Sun, Yixin Cao, Yicun Liu, Keyang Chen, Guangnan Ye, Hongfeng Chai

AI总结:

GAM-RAG通过动态更新检索记忆提升检索增强生成的性能,减少计算成本,提高推理效率。

摘要:

检索增强生成(RAG)通过外部证据来支撑大型语言模型,但许多实现依赖于预构建的索引,这些索引在构建后保持静态。因此,相关查询会重复类似的多步遍历,增加延迟和计算量。受认知神经科学中基于模式的学习启发,我们提出GAM-RAG,一种无需训练的框架,该框架从重复或相关查询中积累检索经验,并随时间更新检索记忆。GAM-RAG构建了一个轻量级、无关系的分层索引,其链接捕捉潜在的共现而非固定的语义关系。在推理过程中,成功的检索事件提供句子级别的反馈,更新句子记忆,使对相似推理类型的有用证据更容易被激活。为在嘈杂反馈下平衡稳定性和适应性,我们引入了基于不确定性的、受卡尔曼启发的增益规则,该规则联合更新记忆状态和基于困惑度的不确定性估计。它对可靠的新信号应用快速更新,对稳定或嘈杂的记忆应用保守的细化。我们提供了更新动态的理论分析,并实证表明,GAM-RAG在最强基线下将平均性能提高3.95%,在使用5轮记忆时提高8.19%,同时将推理成本降低61%。我们的代码和数据集可在:https://anonymous.4open.science/r/GAM_RAG-2EF6获取。

英文摘要:

Retrieval-Augmented Generation (RAG) grounds large language models with external evidence, but many implementations rely on pre-built indices that remain static after construction. Related queries therefore repeat similar multi-hop traversal, increasing latency and compute. Motivated by schema-based learning in cognitive neuroscience, we propose GAM-RAG, a training-free framework that accumulates retrieval experience from recurring or related queries and updates retrieval memory over time. GAM-RAG builds a lightweight, relation-free hierarchical index whose links capture potential co-occurrence rather than fixed semantic relations. During inference, successful retrieval episodes provide sentence-level feedback, updating sentence memories so evidence useful for similar reasoning types becomes easier to activate later. To balance stability and adaptability under noisy feedback, we introduce an uncertainty-aware, Kalman-inspired gain rule that jointly updates memory states and perplexity-based uncertainty estimates. It applies fast updates for reliable novel signals and conservative refinement for stable or noisy memories. We provide a theoretical analysis of the update dynamics, and empirically show that GAM-RAG improves average performance by 3.95% over the strongest baseline and by 8.19% with 5-turn memory, while reducing inference cost by 61%. Our code and datasets are available at: https://anonymous.4open.science/r/GAM_RAG-2EF6.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑