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

Takayuki Semitsu, Naoto Kiribuchi, Kengo Zenitani


Abstract
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.
Anthology ID:
2026.politicalnlp-1.30
Volume:
Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Haithem Afli, Houda Bouamor, Wajdi Zaghouani, Sahar Ghannay, Shehenaz Hossain
Venues:
PoliticalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
284–301
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-politicalnlp-30
DOI:
10.63317/4yuq3ezxohee
Bibkey:
Cite (ACL):
Takayuki Semitsu, Naoto Kiribuchi, and Kengo Zenitani. 2026. Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approach. In Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026), pages 284–301, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approach (Semitsu et al., PoliticalNLP 2026)
Copy Citation: