Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approach

Computer Science > Artificial Intelligence [Submitted on 4 Apr 2026] Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approach Takayuki Semitsu, Naoto Kiribuchi, Kengo Zenitani We present an automated crosswalk framework that compares an AI safety policy document pair under a shared taxonomy of activities. Using the activity categories defined in Activity Map on AI Safety as fixed aspects, the system extracts and maps relevant activities, then produces for each aspect a short summary for each document, a brief comparison, and a similarity score. We assess the stability and validity of LLM-based crosswalk analysis across public policy documents. Using five large language models, we perform crosswalks on ten publicly available documents and visualize mean similarity scores with a heatmap. The results show that model choice substantially affects the crosswalk outcomes, and that some document pairs yield high disagreements across models. A human evaluation by three experts on two document pairs shows high inter-annotator agreement, while model scores still differ from human judgments. These findings support comparative inspection of policy documents. Comments: 18 pages, 6 figures, 6 tables, to be published in PoliticalNLP 2026 Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.03533 [cs.AI]   (or arXiv:2604.03533v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.03533 Focus to learn more Submission history From: Naoto Kiribuchi [view email] [v1] Sat, 4 Apr 2026 01:02:15 UTC (1,428 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)