用于检索增强生成的神经符号检索器
Neurosymbolic Retrievers for Retrieval-augmented Generation
AI总结：
本文提出神经符号 RAG 框架，通过结合知识图谱与神经检索技术，提升检索过程的透明性和生成性能。
摘要：
检索增强生成（RAG）在克服大语言模型的关键限制方面取得了显著进展，例如幻觉、缺乏上下文 grounding 以及透明性问题。然而，传统 RAG 系统由三个相互关联的神经组件——检索器、重排序器和生成器——组成，其内部推理过程仍然不透明。这种不透明性使可解释性变得复杂，阻碍了调试努力，并削弱了信任，尤其是在高风险领域，清晰的决策至关重要。为了解决这些挑战，我们引入了神经符号 RAG 的概念，该概念结合了使用知识图谱的符号推理与神经检索技术。这一新框架旨在回答两个主要问题：（a）检索器能否为文档选择提供清晰且可解释的基础？（b）符号知识能否提高检索过程的清晰度？我们提出了三种方法来改进这种整合。首先，MAR（知识调节对齐检索）利用调节网络通过可解释的符号特征来优化查询嵌入，从而使文档匹配更加明确。其次，KG-Path RAG 通过遍历知识图谱来增强查询，以提高整体检索质量和可解释性。最后，Process Knowledge-infused RAG 利用领域特定工具，根据经过验证的工作流程重新排列检索到的内容。初步结果表明，在心理健康风险评估任务中，这种神经符号方法增强了透明性和整体性能。
英文摘要：
Retrieval Augmented Generation (RAG) has made significant strides in overcoming key limitations of large language models, such as hallucination, lack of contextual grounding, and issues with transparency. However, traditional RAG systems consist of three interconnected neural components - the retriever, re-ranker, and generator - whose internal reasoning processes remain opaque. This lack of transparency complicates interpretability, hinders debugging efforts, and erodes trust, especially in high-stakes domains where clear decision-making is essential. To address these challenges, we introduce the concept of Neurosymbolic RAG, which integrates symbolic reasoning using a knowledge graph with neural retrieval techniques. This new framework aims to answer two primary questions: (a) Can retrievers provide a clear and interpretable basis for document selection? (b) Can symbolic knowledge enhance the clarity of the retrieval process? We propose three methods to improve this integration. First is MAR (Knowledge Modulation Aligned Retrieval) that employs modulation networks to refine query embeddings using interpretable symbolic features, thereby making document matching more explicit. Second, KG-Path RAG enhances queries by traversing knowledge graphs to improve overall retrieval quality and interpretability. Lastly, Process Knowledge-infused RAG utilizes domain-specific tools to reorder retrieved content based on validated workflows. Preliminary results from mental health risk assessment tasks indicate that this neurosymbolic approach enhances both transparency and overall performance
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。
