# Analysis of Threat-Based Manipulation in Large Language Models: A Dual Perspective on Vulnerabilities and Performance Enhancement Opportunities

arXiv: https://arxiv.org/abs/2507.21133 · HTML: https://mlsanity.com/paper/2507.21133/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 7 of 7)

- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [In conversation with Artificial Intelligence: aligning language models with human values](https://mlsanity.com/paper/2209.00731/) (2022)

## Abstract (arXiv)

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.