Problem
Research questions and friction points this paper is trying to address.
Enterprise AI assistants
verifiable and traceable
retrieval augmented generation (RAG)
citation drift
unsupported content
EvidenT: Building Trustworthy Enterprise Assistants through Evidence Groundedness and Traceability
🤖 AI Summary
为解决企业AI助手生成内容的可验证性和追溯性问题，EvidenT通过在答案生成前验证提取证据与文档的一致性来提高信息准确性。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
EvidenT
Evidence Groundedness
Traceability
Citation Drift
Lexical Alignment
🔎 Similar Papers
No similar papers found.
