快速而忠实：长文档检索增强生成系统中的实时验证
Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
AI总结：
本文提出一种实时验证组件，用于长文档检索增强生成系统，通过平衡响应时间和验证覆盖度，提升对长文档的忠实性验证。
摘要：
检索增强生成（RAG）正被越来越多地应用于企业搜索和以文档为中心的助手，其中响应必须基于长且复杂的源材料。在实践中，验证生成答案是否忠实反映检索文档是困难的：大语言模型可以检查长上下文，但对交互服务来说速度和成本太高，而轻量级分类器在严格上下文限制下经常错过截断段落外的证据。我们提出了一个实时验证组件的设计，将其集成到生产RAG管道中，以在延迟限制下实现全文档接地。系统可处理高达32K个标记的文档，并采用自适应推理策略，在不同工作负载中平衡响应时间和验证覆盖度。我们描述了部署验证器的架构决策、操作权衡和评估方法，并展示了全上下文验证相比截断验证在检测不支持响应方面有显著提升。我们的经验突显了长上下文验证的必要性，解释了基于块的检查在真实文档中为何经常失败，以及延迟预算如何影响模型设计。这些发现为构建可靠的大规模检索增强应用的实践者提供了指导。（模型、基准和代码：https://huggingface.co/llm-semantic-router）
英文摘要：
Retrieval-augmented generation (RAG) is increasingly deployed in enterprise search and document-centric assistants, where responses must be grounded in long and complex source materials. In practice, verifying that generated answers faithfully reflect retrieved documents is difficult: large language models can check long contexts but are too slow and costly for interactive services, while lightweight classifiers operate within strict context limits and frequently miss evidence outside truncated passages. We present the design of a real-time verification component integrated into a production RAG pipeline that enables full-document grounding under latency constraints. The system processes documents up to 32K tokens and employs adaptive inference strategies to balance response time and verification coverage across workloads. We describe the architectural decisions, operational trade-offs, and evaluation methodology used to deploy the verifier, and show that full-context verification substantially improves detection of unsupported responses compared with truncated validation. Our experience highlights when long-context verification is necessary, why chunk-based checking often fails in real documents, and how latency budgets shape model design. These findings provide practical guidance for practitioners building reliable large-scale retrieval-augmented applications. (Model, benchmark, and code: https://huggingface.co/llm-semantic-router)
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。
