← 피드로
[Submitted on 15 Sep 2026]
Abstract: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%.
Submission history
From: Mohammadreza Sediqin [view email]
[v1]
Tue, 15 Sep 2026 19:37:46 UTC (163 KB)
추출 본문 · 출처: arxiv.org · https://arxiv.org/abs/2609.17775