Saved in:
Bibliographic Details
Main Authors: Semitsu, Takayuki, Kiribuchi, Naoto, Zenitani, Kengo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.03533
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914445406502912
author Semitsu, Takayuki
Kiribuchi, Naoto
Zenitani, Kengo
author_facet Semitsu, Takayuki
Kiribuchi, Naoto
Zenitani, Kengo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03533
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approach
Semitsu, Takayuki
Kiribuchi, Naoto
Zenitani, Kengo
Artificial Intelligence
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.
title Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approach
topic Artificial Intelligence
url https://arxiv.org/abs/2604.03533