---
title: "GB/T-Bench: Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.06312v1"
permalink: "https://feed.astralor.com/items/itm_0c1fb709004937241a2f75ff"
published: "2026-08-06T17:27:23.000Z"
score: 82
channel: "ai"
tags: ["arXiv","GB/T-Bench","GB/T-Reviewer","Multi-agent framework","Benchmark"]
---

# GB/T-Bench: Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents

## AI commentary

> This paper deserves attention from anyone working on document intelligence and professional AI review. It is not just another benchmark; it breaks down rule-intensive review—a scenario that was heavily human-dependent—into quantifiable tasks for the first time. For professionals in standardization, legal tech, and compliance tech, the methodology can be directly transferred to contracts, regulations, and industry norms. The multi-agent framework's gain is also compelling—from 0.328 to 0.509—showing that structured skill coordination can indeed unlock LLM potential.

## At a glance

Large language models are increasingly used in complex professional tasks, yet their capabilities in rule-intensive document review remain underevaluated. The team introduces GB/T-Bench, the first benchmark for structured review of national standard documents, featuring a hierarchical review taxonomy, 25 diagnosable error types, and a controllable counterexample generation mechanism, processing 488 documents into 7,306 traceable error instances. They also propose GB/T-Reviewer, a multi-agent framework that converts review knowledge into specialized skills and coordinates global inspection, targeted diagnosis, rule scanning, and result verification. Experiments with 14 mainstream LLMs reveal a substantial human-LLM gap: the strongest model achieves only 0.3280 CMCS versus 0.6640 for experts, while GB/T-Reviewer raises the best CMCS to 0.5094, paving the way for trustworthy AI in standardization and other high-stakes document domains.

## Key points

- GB/T-Bench is the first benchmark for structured review of national standard documents, defining 25 diagnosable error types.
- A controllable counterexample generation mechanism combines deterministic rules and constrained LLM rewriting to produce 7,306 traceable review error instances.
- Experiments show a significant human-LLM gap, and the multi-agent framework GB/T-Reviewer raises the best CMCS to 0.5094.

## Full text

Large language models (LLMs) increasingly support complex professional tasks, yet their capabilities in rule-intensive document review remain insufficiently evaluated. National standard documents, such as China GB/T standards, offer a representative testbed: they are lengthy, highly structured, and governed by explicit rules for scope, terminology, normative wording, and cross-section consistency. Existing benchmarks focus on domain knowledge and question answering, largely overlooking intrinsic quality review for professional documents. Such reviews rely heavily on human experts, making them costly and difficult to scale. To bridge this gap, we introduce GB/T-Bench, the first benchmark for the structured review of national standard documents. Its GB/T Review Taxonomy is a hierarchical schema covering document structure, scope alignment, normative modality, terminology consistency, and normative references, with 25 diagnosable error types. A controllable counterexample generation mechanism combines deterministic rules and constrained LLM rewriting to process 488 documents into 7,306 traceable review error instances for evaluation. We also develop a diagnosis-oriented evaluation protocol requiring exact matches on error location, review dimension, and error type, plus document-level coverage metrics. We further propose GB/T-Reviewer, a multi-agent framework that converts review knowledge into specialized skills and coordinates global inspection, targeted diagnosis, rule scanning, and result verification. Experiments with 14 mainstream LLMs reveal a substantial human-LLM gap: the strongest model achieves only 0.3280 CMCS versus 0.6640 for experts. GB/T-Reviewer raises the best CMCS to 0.5094, showing the value of structured skill coordination for rule-intensive document review. This work paves the way for trustworthy AI in standardization and other high-stakes document domains.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_0c1fb709004937241a2f75ff