arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.12436cs.CL
收藏

我应该信任你吗?使用反事实强化学习检测谈判中的欺骗行为

Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL

Department of Computer Science, University of Maryland(大学计算机科学系);Northwestern University(西北大学);School of Computer Science, University of Sydney(悉尼大学计算机科学学院);Information Sciences Institute, University of Southern California(南加州大学信息科学研究所)

Wichayaporn Wongkamjan, Yanze Wang, Feng Gu, Denis Peskoff, Jonathan K. Kummerfeld, Jonathan May, Jordan Lee Boyd-Graber

AI总结:

本文针对谈判中“好得令人难以置信”的欺骗性提议,提出结合反事实强化学习与文本特征的方法,在《外交》游戏中以高精确率检测人类欺骗,优于大语言模型方法,并为人机交互中的摩擦机制提供基础。

摘要:

一个日益普遍的社会技术问题是人们被听起来“好得令人难以置信”的提议所欺骗,其中说服与信任塑造了决策过程。本文研究人工智能如何帮助检测这些欺骗性场景。我们分析了人类在《外交》(Diplomacy)这款既需要自然语言交流又需要战略推理的棋盘游戏中如何策略性地相互欺骗。这需要从玩家通信中提取拟议协议的逻辑形式,并利用智能体的价值函数计算提议的相对奖励。结合基于文本的特征,这可以改进我们的欺骗检测。与一种将许多真实消息误标为欺骗性消息的大语言模型方法相比,我们的方法以高精确率检测人类欺骗行为。未来的人机交互工具可以基于我们的欺骗检测方法,通过触发“摩擦”来给用户提供质疑可疑提议的机会。

英文摘要:

An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive scenarios. We analyze how humans strategically deceive each other in \textit{Diplomacy}, a board game that requires both natural language communication and strategic reasoning. This requires extracting logical forms of proposed agreements in player communications and computing the relative rewards of the proposal using agents' value functions. Combined with text-based features, this can improve our deception detection. Our method detects human deception with a high precision when compared to a Large Language Model approach that flags many true messages as deceptive. Future human-\abr{ai} interaction tools can build on our methods for deception detection by triggering \textit{friction} to give users a chance of interrogating suspicious proposals.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑