Towards Strategic Persuasion with Language Models
This work addresses the problem of scalable and principled assessment of LLM persuasion for researchers and practitioners, though it is incremental as it adapts existing frameworks and datasets.
The paper tackles the challenge of systematically evaluating the persuasive capabilities of large language models (LLMs) by developing a theory-driven framework based on Bayesian Persuasion, using existing human-human datasets to create evaluation environments. The results show that frontier models achieve high persuasion gains and exhibit sophisticated strategies, and reinforcement learning enables even small LLMs to obtain significantly higher persuasion gains.
Large language models (LLMs) have demonstrated strong persuasive capabilities comparable to those of humans, offering promising benefits while raising societal concerns about their deployment. However, systematically evaluating the persuasive capabilities of LLMs is inherently challenging, as the effectiveness of persuasion among humans varies significantly across different domains. In this paper, we take a theory-driven approach to provide a scalable and principled framework for measuring the persuasive capabilities of LLMs. Grounded in the Bayesian Persuasion (BP) framework, we repurpose existing human-human persuasion datasets to construct environments for evaluating and training LLMs in strategic persuasion. Our results reveal that frontier models can consistently achieve high persuasion gains and exhibit sophisticated persuasion strategies that align with theoretical predictions. Building on this, we use reinforcement learning to train LLMs for strategic persuasion in our environments. Our results also demonstrate that even small LLMs can obtain significantly higher persuasion gains through reinforcement learning.