双向RAG：通过多阶段验证实现安全的自我改进检索增强生成
Bidirectional RAG: Safe Self-Improving Retrieval-Augmented Generation Through Multi-Stage Validation
AI总结：
双向RAG通过多阶段验证实现安全的自我改进检索增强生成，提高了覆盖率并减少了文档数量，展示了RAG系统在严格验证下的可行性。
摘要：
检索增强生成（RAG）系统通过将响应基于外部知识库来增强大型语言模型，但传统RAG架构使用静态语料库，无法从用户交互中进化。我们引入了双向RAG，一种新的RAG架构，通过验证的写回高质量生成响应来实现安全的语料库扩展。我们的系统采用多阶段接受层，结合接地验证（基于NLI的蕴含、属性检查和新颖性检测），以防止幻觉污染的同时实现知识积累。在四个数据集（自然问题、 triviaQA、 HotpotQA、 Stack Overflow）上，使用三个随机种子进行12次实验，双向RAG实现了40.58%的平均覆盖率，几乎翻倍于标准RAG的20.33%，同时比朴素写回方法（140 vs 500）增加了72%更少的文档。我们的工作表明，当由严格验证指导时，自我改进RAG是可行且安全的，为能够从部署中学习的RAG系统提供了一条实际路径。
英文摘要：
Retrieval-Augmented Generation RAG systems enhance large language models by grounding responses in external knowledge bases, but conventional RAG architectures operate with static corpora that cannot evolve from user interactions. We introduce Bidirectional RAG, a novel RAG architecture that enables safe corpus expansion through validated write back of high quality generated responses. Our system employs a multi stage acceptance layer combining grounding verification (NLI based entailment, attribution checking, and novelty detection to prevent hallucination pollution while enabling knowledge accumulation. Across four datasets Natural Questions, TriviaQA, HotpotQA, Stack Overflow with three random seeds 12 experiments per system, Bidirectional RAG achieves 40.58% average coverage nearly doubling Standard RAG 20.33% while adding 72% fewer documents than naive write back 140 vs 500. Our work demonstrates that self improving RAG is feasible and safe when governed by rigorous validation, offering a practical path toward RAG systems that learn from deployment.
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。
