On the Adaptive Psychological Persuasion of Large Language Models

TL;DR

This paper investigates how large language models can be guided to adopt effective psychological persuasion strategies, improving their success rates in adversarial dialogues through an adaptive framework that learns to select optimal tactics.

Contribution

It introduces an adaptive framework based on preference optimization that enables LLMs to autonomously select effective persuasion strategies, significantly improving their success in psychological persuasion tasks.

Findings

Explicit strategies like Fluency and Repetition improve persuasion success.

No single strategy is universally effective across contexts.

The adaptive framework enhances success rates across multiple LLMs.

Abstract

Previous work has showcased the intriguing capabilities of Large Language Models (LLMs) in instruction-following and rhetorical fluency. However, systematic exploration of their dual capabilities to autonomously persuade and resist persuasion, particularly in contexts involving psychological rhetoric, remains unexplored. In this paper, we first evaluate four commonly adopted LLMs by tasking them to alternately act as persuaders and listeners in adversarial dialogues. Empirical results show that persuader LLMs predominantly employ repetitive strategies, leading to low success rates. Then we introduce eleven comprehensive psychological persuasion strategies, finding that explicitly instructing LLMs to adopt specific strategies such as Fluency Effect and Repetition Effect significantly improves persuasion success rates. However, no ``one-size-fits-all'' strategy proves universally effective, with performance heavily dependent on contextual counterfactuals. Motivated by these observations, we propose an adaptive framework based on direct preference optimization that trains LLMs to autonomously select optimal strategies by leveraging persuasion results from strategy-specific responses as preference pairs. Experiments on three open-source LLMs confirm that the proposed adaptive psychological persuasion method effectively enables persuader LLMs to select optimal strategies, significantly enhancing their success rates while maintaining general capabilities. Our code is available at https://github.com/KalinaEine/PsychologicalPersuasion.