谎言，该死的谎言，以及分布式的语言统计：使用大型语言模型进行说服与欺骗
Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models
AI总结：
本综述综合了近期关于LLMs说服与欺骗能力的实证研究，分析了相关理论风险并评估了缓解措施，指出微调和多模态等机制可能增强其影响，同时提出了未来研究的关键开放性问题。
摘要：
大型语言模型（LLMs）能够生成与人类撰写文本一样具有说服力的内容，并且似乎能够选择性地产生欺骗性输出。随着这些系统被更广泛地部署，这些能力引发了人们对潜在滥用和意外后果的担忧。本综述综合了近期考察LLMs在说服和欺骗方面的能力与倾向的实证研究，分析了可能由这些能力引发的理论风险，并评估了拟议的缓解措施。虽然当前的说服效果相对较小，但包括微调、多模态和社交因素在内的各种机制可能会增加其影响。我们概述了未来研究的关键开放性问题，包括AI系统可能会变得多么具有说服力，真相是否比虚假信息享有固有的优势，以及不同的缓解策略在实践中可能有多有效。
英文摘要：
Large Language Models (LLMs) can generate content that is as persuasive as human-written text and appear capable of selectively producing deceptive outputs. These capabilities raise concerns about potential misuse and unintended consequences as these systems become more widely deployed. This review synthesizes recent empirical work examining LLMs' capacity and proclivity for persuasion and deception, analyzes theoretical risks that could arise from these capabilities, and evaluates proposed mitigations. While current persuasive effects are relatively small, various mechanisms could increase their impact, including fine-tuning, multimodality, and social factors. We outline key open questions for future research, including how persuasive AI systems might become, whether truth enjoys an inherent advantage over falsehoods, and how effective different mitigation strategies may be in practice.
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。
