Persuasion Games using Large Language Models
Ganesh Prasath Ramani, Shirish Karande, Santhosh V, Yash Bhatia
TL;DR
The paper investigates how large language models can be used to influence user decisions across domains such as insurance, banking, and retail by deploying a multi-agent persuasion framework. It introduces a four-agent chat system (Conversation, Advisor, Moderator, Retrieval) that leverages emotion detection, resistance mapping, information retrieval, strategy formulation, and fact verification to produce persuasive yet grounded dialogue. The study deploys simulated personas to assess both the ability to persuade and the susceptibility to resistance, employing action-focused metrics (buy/visit/need details/no buy) alongside pre/post surveys and language analyses. Key findings show that while LLM-powered persuasion can drive perspective changes and purchases, introducing emotional modifiers can dampen effectiveness and longer, more information-rich conversations may be required to avoid premature termination; future work targets improved domain grounding and agent memory/tools to enhance real-time decision-making. Overall, the work demonstrates the feasibility of orchestrating persuasive LLM-driven dialogue with measurable outcomes, while highlighting the need for robust grounding and memory to sustain effective interactions in real-world settings.
Abstract
Large Language Models (LLMs) have emerged as formidable instruments capable of comprehending and producing human-like text. This paper explores the potential of LLMs, to shape user perspectives and subsequently influence their decisions on particular tasks. This capability finds applications in diverse domains such as Investment, Credit cards and Insurance, wherein they assist users in selecting appropriate insurance policies, investment plans, Credit cards, Retail, as well as in Behavioral Change Support Systems (BCSS). We present a sophisticated multi-agent framework wherein a consortium of agents operate in collaborative manner. The primary agent engages directly with user agents through persuasive dialogue, while the auxiliary agents perform tasks such as information retrieval, response analysis, development of persuasion strategies, and validation of facts. Empirical evidence from our experiments demonstrates that this collaborative methodology significantly enhances the persuasive efficacy of the LLM. We continuously analyze the resistance of the user agent to persuasive efforts and counteract it by employing a combination of rule-based and LLM-based resistance-persuasion mapping techniques. We employ simulated personas and generate conversations in insurance, banking, and retail domains to evaluate the proficiency of large language models (LLMs) in recognizing, adjusting to, and influencing various personality types. Concurrently, we examine the resistance mechanisms employed by LLM simulated personas. Persuasion is quantified via measurable surveys before and after interaction, LLM-generated scores on conversation, and user decisions (purchase or non-purchase).