Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents

• URL: http://arxiv.org/abs/2608.06312v1
• Date: Thu, 06 Aug 2026 17:27:23 GMT
• Title: Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents
• Abstract summary: Large language models (LLMs) increasingly support complex professional tasks, yet their capabilities in rule-intensive document review remain insufficiently evaluated.<n>Existing benchmarks focus on domain knowledge and question answering, largely overlooking quality review for professional documents.<n>We introduce GB/T-Bench, the first benchmark for the structured review of national standard documents.
• Score: 7.397429318828859
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation [54.82704239643649]
  We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans.<n>Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can therefore provide latent supervision for revision-oriented feedback.<n>We also introduce ActReview-Bench, a human-curated benchmark of 1,000 instances for evaluating diagnostic quality and revision usefulness.
  arXiv  Detail & Related papers  (2026-09-08T17:30:16Z)
• Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing [53.41293908252118]
  We introduce Dr. DocBench, a difficulty-aware benchmark for expert-level document parsing.<n>Dr. DocBench spans 52 BISAC domains and selects documents through failure-based sampling.<n>It contains 4,514 annotated pages from long documents averaging around 100 pages, with 65k high-quality annotations for layout, reading order, hierarchical relations, and domain-specific visual contents.<n>Our analysis reveals substantial failures across subjects, content types, and structural attributes, highlighting Dr. DocBench as a comprehensive testbed for diagnosing and advancing document intelligence.
  arXiv  Detail & Related papers  (2026-05-31T18:35:30Z)
• RWGBench: Evaluating Scholarly Positioning in Related Work Generation [43.26813089097539]
  We introduce textbfRWGBench, a benchmark that evaluates RWG from the perspective of citation decision-making rather than text similarity.<n>RWGBench is constructed from a large-scale collection of 40,108 computer science papers and a retrieval corpus of 1.09 million documents.<n>Experiments reveal systematic limitations in current systems that are obscured by standard evaluations, while Oracle studies further disentangle retrieval-level and generation-level bottlenecks.
  arXiv  Detail & Related papers  (2026-05-30T16:53:14Z)
• RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora [11.316299961548415]
  We present a framework for constructing realistic benchmarks by decomposing documents into atomic facts.<n>We also present RedQA, where a strong retriever baseline drops from 66.4% PerfRecall@10 on 4-hop General-Wiki to 5.0-27.9% PerfRecall@10 at 4-hop depth.
  arXiv  Detail & Related papers  (2026-04-21T03:54:09Z)
• ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents [50.27474750319121]
  Review text according to paper-specific rubrics derived from official guidelines, the paper's content, and human-written reviews.<n>We introduce REVIEWBENCH, a benchmark evaluating review text according to paper-specific rubrics derived from official guidelines, the paper's content, and human-written reviews.<n>We propose REVIEWGROUNDER, a rubric-guided, tool-integrated multi-agent framework that decomposes reviewing into drafting and grounding stages.
  arXiv  Detail & Related papers  (2026-04-15T16:33:04Z)
• Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles [56.724847946825285]
  We introduce Wiki Live Challenge (WLC), a live benchmark that leverages the newest Wikipedia Good Articles (GAs) as expert-level references.<n>We propose Wiki Eval, a comprehensive evaluation framework comprising a fine-grained evaluation method with 39 criteria for writing quality and rigorous metrics for factual verifiability.
  arXiv  Detail & Related papers  (2026-02-02T03:30:13Z)
• RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension [65.81339691942757]
  RPC-Bench is a large-scale question-answering benchmark built from review-rebuttal exchanges of high-quality computer science papers.<n>We design a fine-grained taxonomy aligned with the scientific research flow to assess models' ability to understand and answer why, what, and how questions in scholarly contexts.
  arXiv  Detail & Related papers  (2026-01-14T11:37:00Z)
• DEER: A Comprehensive and Reliable Benchmark for Deep-Research Expert Reports [49.217247659479476]
  deep research systems can generate expert-level reports via multi-step reasoning and evidence-based synthesis.<n>Existing benchmarks often lack systematic criteria for expert reporting.<n>We introduce DEER, a benchmark for evaluating expert-level deep research reports.
  arXiv  Detail & Related papers  (2025-12-19T16:46:20Z)
• LegalRikai: Open Benchmark - A Benchmark for Complex Japanese Corporate Legal Tasks [2.399077824457897]
  This paper introduces LegalRikai: Open Benchmark, a new benchmark comprising four complex tasks that emulate Japanese corporate legal practices.<n>This benchmark has 100 samples that require long-form, structured outputs, and we evaluated them against multiple practical criteria.
  arXiv  Detail & Related papers  (2025-12-12T05:47:06Z)
• DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM [35.910677096654574]
  Document parsing aims to transform unstructured PDF images into semi-structured data, facilitating the digitization and utilization of information in diverse domains.<n>Common practice often selects the top-performing model on standard benchmarks.<n>We introduce DOCR-Inspector, which formalizes document parsing assessment as fine-grained error detection and analysis.
  arXiv  Detail & Related papers  (2025-12-11T13:16:33Z)
• Expert Preference-based Evaluation of Automated Related Work Generation [54.29459509574242]
  We propose GREP, a multi-turn evaluation framework that integrates classical related work evaluation criteria with expert-specific preferences.<n>For better accessibility, we design two variants of GREP: a more precise variant with proprietary LLMs as evaluators, and a cheaper alternative with open-weight LLMs.
  arXiv  Detail & Related papers  (2025-08-11T13:08:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.