Towards Automated Quality Assurance of Patent Specifications: A Multi-Dimensional LLM Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chai, Yuqian, Wang, Chaochao, Wang, Weilei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918178179776512
author Chai, Yuqian
Wang, Chaochao
Wang, Weilei
author_facet Chai, Yuqian
Wang, Chaochao
Wang, Weilei
contents Although AI drafting tools have gained prominence in patent writing, the systematic evaluation of AI-generated patent content quality represents a significant research gap. To address this gap, We propose to evaluate patents using regulatory compliance, technical coherence, and figure-reference consistency detection modules, and then generate improvement suggestions via an integration module. The framework is validated on a comprehensive dataset comprising 80 human-authored and 80 AI-generated patents from two patent drafting tools. Evaluation is performed on 10,841 total sentences, 8,924 non-template sentences, and 554 patent figures for the three detection modules respectively, achieving balanced accuracies of 99.74%, 82.12%, and 91.2% against expert annotations. Additional analysis was conducted to examine defect distributions across patent sections, technical domains, and authoring sources. Section-based analysis indicates that figure-text consistency and technical detail precision require particular attention. Mechanical Engineering and Construction show more claim-specification inconsistencies due to complex technical documentation requirements. AI-generated patents show a significant gap compared to human-authored ones. While human-authored patents primarily contain surface-level errors like typos, AI-generated patents exhibit more structural defects in figure-text alignment and cross-references.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25402
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Automated Quality Assurance of Patent Specifications: A Multi-Dimensional LLM Framework
Chai, Yuqian
Wang, Chaochao
Wang, Weilei
Information Retrieval
Computational Engineering, Finance, and Science
Although AI drafting tools have gained prominence in patent writing, the systematic evaluation of AI-generated patent content quality represents a significant research gap. To address this gap, We propose to evaluate patents using regulatory compliance, technical coherence, and figure-reference consistency detection modules, and then generate improvement suggestions via an integration module. The framework is validated on a comprehensive dataset comprising 80 human-authored and 80 AI-generated patents from two patent drafting tools. Evaluation is performed on 10,841 total sentences, 8,924 non-template sentences, and 554 patent figures for the three detection modules respectively, achieving balanced accuracies of 99.74%, 82.12%, and 91.2% against expert annotations. Additional analysis was conducted to examine defect distributions across patent sections, technical domains, and authoring sources. Section-based analysis indicates that figure-text consistency and technical detail precision require particular attention. Mechanical Engineering and Construction show more claim-specification inconsistencies due to complex technical documentation requirements. AI-generated patents show a significant gap compared to human-authored ones. While human-authored patents primarily contain surface-level errors like typos, AI-generated patents exhibit more structural defects in figure-text alignment and cross-references.
title Towards Automated Quality Assurance of Patent Specifications: A Multi-Dimensional LLM Framework
topic Information Retrieval
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2510.25402