Geographic Blind Spots in AI Control Monitors: A Cross-National Audit of Claude Opus 4.6

TL;DR

This study audits the geographic knowledge gaps of Claude Opus 4.6, revealing unexpected higher fabrication rates in Global North contexts, which pose risks for AI control reliability across countries.

Contribution

It introduces the AI Control Knowledge Framework (ACKF) and provides the first cross-national audit of AI control monitor geographic knowledge gaps.

Findings

Claude Opus 4.6 has higher fabrication rates for Global North queries.

Global North contexts are more prone to incorrect responses, contrary to initial expectations.

The study highlights a vulnerability that could be exploited to evade AI control detection.

Abstract

Artificial intelligence (AI) control protocols assume that trusted large language model (LLM) monitors reliably assess proposed actions across all deployment contexts. This paper tests that assumption in the geographic dimension. We audit Claude Opus 4.6-the monitor specified in Apart Research's AI Control Hackathon Track 3 benchmark-for systematic gaps in its factual knowledge of the global AI landscape. We develop the AI Control Knowledge Framework (ACKF), a six-dimension thematic scheme, and operationalise it with 17 verified indicators drawn from the Global AI Dataset v2 (GAID v2): 24,453 indicators across 227 countries published on Harvard Dataverse. A five-category response classification scheme distinguishes verifiable fabrication (VF) from honest refusal (HR); logistic regression with country-clustered standard errors combined with difference-in-differences (DiD) estimation quantifies geographic disparities in monitor accuracy across 2,820 country-metric-year observations. Contrary to our initial hypothesis, Claude Opus 4.6 produces higher fabrication rates for Global North queries than for Global South counterparts-a pattern consistent with a partial-knowledge mechanism in which the model attempts answers more frequently for Global North contexts but commits to incorrect values. This fabrication profile constitutes an exploitable vulnerability, where an adversarial AI system could frame harmful actions in governance or public attitude terms to reduce the probability of detection. This study provides the first cross-national, multi-domain audit of an AI control monitor's geographic knowledge gaps, with direct implications for the design of control protocols.