SAGE：从企业指南中受治理的工件生成

中文摘要 AI 辅助

企业指南文档混合了叙述性文本、复杂表格和嵌入图像，将其转换为结构化工作工件目前每份仍需两到三天的人工工作量。当前的语言和视觉语言模型能从此类文档中提取信息，但除提取外不提供受治理的工作流：没有验证、没有一致性检查、没有可追踪的工件生成。我们提出SAGE，一个受治理的多阶段LLM流水线，围绕共享的带版本控制的规则存储组织，该存储具有稳定标识符、经模式验证的阶段间契约以及端到端的溯源追踪。提取的规则经过确定性结构验证和基于LLM的语义评分，然后由一致性模块去除重复项、标记矛盾并暴露规范缺口；仅不确定或标记的项目到达审查者，而高置信度输出被自动批准。在120份文档上，SAGE将周转时间从数天缩短至20-100分钟，实现了96%的文档级成功率，幻觉率为3.2%，提取了3,896条规则并生成了812个可供人工审查的工件；若无治理，幻觉率升至15.7%。

英文摘要

Enterprise guideline documents mix narrative text, complex tables, and embedded images, and converting them into structured work artifacts still takes two to three days of manual effort each. Current language and vision-language models extract from such documents but offer no governed workflow beyond extraction: no validation, no consistency checking, no traceable artifact generation. We introduce SAGE, a governed multi-stage LLM pipeline organized around a shared versioned rule store with stable identifiers, schema-validated inter-stage contracts, and end-to-end provenance tracking. Extracted rules undergo deterministic structural validation and LLM-based semantic scoring, then a consistency module that removes duplicates, flags contradictions, and surfaces specification gaps; only uncertain or flagged items reach reviewers, while high-confidence outputs are auto-approved. On 120 documents, SAGE cuts turnaround from days to 20-100 minutes, achieving a 96% document-level success rate with 3.2% hallucination, extracting 3,896 rules and producing 812 artifacts ready for human review; without governance, hallucination rises to 15.7%.

发表机构

• Centific Research

机构由 AI 辅助整理，请以论文原文为准。