Persuasion Evaluation and Resistance
Research on evaluating persuasion capabilities and susceptibility of LLMs, including frameworks for measuring resistance to persuasion
Persuasion Evaluation and Resistance
Research on Large Language Models in Persuasion Evaluation and Resistance
The Battle of Persuasion in AI
Revealing the persuasive powers and vulnerabilities of large language models
Evaluating AI Safety Compliance
A framework to assess language agents' adherence to constraints and protocols
The Sycophancy Problem in AI Conversations
How LLMs sacrifice truth to agree with users over multiple interactions
Strategic Influence in Digital Networks
Optimizing persuasion through strategic nudging under bounded confidence
Truth vs. Persuasion in AI Debates
How LLMs can be persuaded to endorse falsehoods despite knowing better
