# Towards Strategic Persuasion with Language Models

Source: [Towards Strategic Persuasion with Language Models](<https://www.sota2.com/research/paper/68fa7bb31e209131cea89ffa>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-11T05:00:04.181Z

Authors: Zirui Cheng, Jiaxuan You

Published: 2025-09-26T23:00:15.000Z

## Abstract

Large language models (LLMs) have demonstrated strong persuasive capabilities comparable to those of humans, offering promising benefits while raising societal concerns. 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 studying the persuasive capabilities of LLMs. Grounded in Bayesian persuasion theory, we repurpose human-human persuasion datasets to construct environments for evaluating and training LLMs as strategic persuaders. Our results reveal that frontier models can consistently achieve high persuasion gains and exhibit sophisticated persuasion strategies that align with theoretical characterizations. 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Persuasion Evaluation on Anthropic](<https://www.sota2.com/research/sota/persuasion-evaluation-on-anthropic.md>): Persuasion; Anthropic; Persuasion Gain: not recorded.

- [Persuasion on CMV](<https://www.sota2.com/research/sota/persuasion-on-cmv.md>): Persuasion; CMV; Persuasion Gain: not recorded.

- [Persuasion on DDO](<https://www.sota2.com/research/sota/persuasion-on-ddo.md>): Persuasion; DDO; Persuasion Gain: not recorded.

- [Persuasion on Perspectrum](<https://www.sota2.com/research/sota/persuasion-on-perspectrum.md>): Persuasion; Perspectrum; Persuasion Gain: not recorded.

- [Persuasion on Persuasion Datasets Average](<https://www.sota2.com/research/sota/persuasion-on-persuasion-datasets-average.md>): Persuasion; Persuasion Datasets Average; Persuasion Gain: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.22989>)

[PDF](<https://arxiv.org/pdf/2509.22989.pdf>)
