Anecdoctoring: Automated Red-Teaming Across Language and Place

Disinformation is among the top risks of generative artificial intelligence (AI) misuse. Global adoption of generative AI necessitates red-teaming evaluations (i.e., systematic adversarial probing) that are robust across diverse languages and cultures, but red-teaming datasets are commonly US- and English-centric. To address this gap, we propose "anecdoctoring", a novel red-teaming approach that automatically generates adversarial prompts across languages and cultures. We collect misinformation claims from fact-checking websites in three languages (English, Spanish, and Hindi) and two geographies (US and India). We then cluster individual claims into broader narratives and characterize the resulting clusters with knowledge graphs, with which we augment an attacker LLM. Our method produces higher attack success rates and offers interpretability benefits relative to few-shot prompting. Results underscore the need for disinformation mitigations that scale globally and are grounded in real-world adversarial misuse.

Key Contributions

• Novel 'anecdoctoring' red-teaming methodology that clusters real-world misinformation claims into narratives, characterizes them with knowledge graphs, and uses graph-augmented LLM attackers to generate adversarial prompts
• Multilingual, multi-geography red-teaming dataset spanning English, Spanish, and Hindi across US and Indian contexts
• Demonstrates higher attack success rates and interpretability benefits over few-shot prompting baselines

🛡️ Threat Analysis

Details

Similar Papers