EvidenT：通过证据基础性和可追溯性构建可信的企业助手
EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability
- Bloomberg（彭博）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对企业AI助手响应可验证性和可追溯性问题，提出轻量级流水线EvidenT，在生成前验证证据并纠正引文漂移，无需重训模型，在500个真实查询上将黄金源命中率平均提升29%。
AI中文摘要：
企业AI助手必须生成可验证且可追溯到源证据的响应。然而，在异构企业数据上进行检索增强生成（RAG）可能会遭遇引文漂移、不支持的内容和较弱的源可追溯性。我们提出了EvidenT（T = 信任 + 透明度 + 可追溯性），这是一个轻量级流水线，在答案生成之前，先对照检索到的文档验证提取的证据，无需模型重新训练。EvidenT将结构化段落提取与确定性词汇对齐相结合，以过滤不支持的内容、纠正引文漂移并保持源跨度可追溯性。在大约500个真实企业查询中，EvidenT相比提示基线，将黄金源命中率平均提高了29%，未产生对未检索URL的引文，并实现了接近饱和的答案到源词汇覆盖率。
英文摘要：
Enterprise AI assistants must produce responses that are verifiable and traceable to source evidence. However, retrieval augmented generation (RAG) over heterogeneous enterprise data can suffer from citation drift, unsupported content, and weak source traceability. We present EvidenT (T = Trust + Transparency + Traceability), a lightweight pipeline that verifies extracted evidence against retrieved documents before answer generation, without model retraining. EvidenT combines structured passage extraction with deterministic lexical alignment to filter unsupported content, correct citation drift, and preserve source-span traceability. On approximately 500 real enterprise queries, EvidenT improves gold-source hit rate by an average of 29% over prompting baselines, produces no citations to nonretrieved urls, and achieves near-saturated answer-to-source lexical coverage.
