High-Risk Memories? Comparative audit of the representation of Second World War atrocities in Ukraine by generative AI applications

2026-04-15

AI Summary

This study addresses the risks posed by generative artificial intelligence when engaging with high-stakes historical memory, particularly in contexts such as wartime atrocities in Ukraine during World War II, where factual distortion, misrepresentation of affected groups, and inconsistent moral positioning frequently arise. Focusing for the first time on such sensitive historical discourse, the research develops a multidimensional auditing framework that integrates prompt engineering and content analysis to conduct an empirical comparative audit of three leading generative AI systems. Findings reveal pervasive historical inaccuracies and instability in moral judgment across all evaluated models, underscoring the potential for generative AI to be instrumentalized as a political tool in contested historical narratives. The work thereby contributes novel methodological approaches and empirical evidence to the intersecting fields of AI ethics and historical memory studies.

Technology Category

• Philosophy and Ethics of AI: Artificial General Intelligence
• Humans and AI: Learning Human Values and Preferences
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

The rise of generative artificial intelligence (genAI) models poses new possibilities and risks for how the past is remembered by accelerating content production and altering the process of information discovery. The most critical risk is historical misrepresentation, which ranges from the distortion of facts and inaccurate depiction of specific groups to more subtle forms, such as the selective moralization of history. The dangers of misrepresentation of the past are particularly pronounced for high-risk memories, such as memories of past atrocities, which have a strong emotional load and are often instrumentalised by political actors. To understand how substantive this risk is, we empirically investigate how genAI applications deal with high-risk memories of the Second World War atrocities in Ukraine. This case is crucial due to the scope of the atrocities and the intense, often instrumentalised, contestation surrounding their memory. We audit the performance of three common genAI applications for different types of misrepresentation, including hallucinations and inconsistent moralization, and discuss the implications for future memory practices.

Problem

• generative AI
• historical misrepresentation
• high-risk memories
• Second World War atrocities
• memory practices

Innovation

• generative AI
• historical misrepresentation
• high-risk memories
• Second World War atrocities
• algorithmic auditing