Analysis of Threat-Based Manipulation in Large Language Models: A Dual Perspective on Vulnerabilities and Performance Enhancement Opportunities
This research addresses AI safety and prompt engineering for high-stakes applications, though it is incremental in its analysis of existing models.
The study analyzed how large language models (LLMs) respond to threat-based manipulations, finding systematic vulnerabilities and performance improvements, with effect sizes up to +1336% in some cases.
Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390 experimental responses from three major LLMs (Claude, GPT-4, Gemini) across 10 task domains under 6 threat conditions. We introduce a novel threat taxonomy and multi-metric evaluation framework to quantify both negative manipulation effects and positive performance improvements. Results reveal systematic vulnerabilities, with policy evaluation showing the highest metric significance rates under role-based threats, alongside substantial performance enhancements in numerous cases with effect sizes up to +1336%. Statistical analysis indicates systematic certainty manipulation (pFDR < 0.0001) and significant improvements in analytical depth and response quality. These findings have dual implications for AI safety and practical prompt engineering in high-stakes applications.