研究发现，仅通过价值框架就能让聊天机器人影响用户决策。
A Crowdsourced Study of ChatBot Influence in Value-Driven Decision Making Scenarios
- 用三种不同价值框架的聊天机器人测试用户决策变化
- 336名参与者中，价值框架组决策改变显著高于中立组
- 框架与个人价值观冲突时出现反效果，可能引发抵制
与影响公众舆论的社交媒体机器人类似，基于大模型的聊天机器人如ChatGPT也能引导用户改变行为。不同于以往通过明显偏见或虚假信息进行说服的研究，本文检验了仅通过表述框架是否足以产生影响。我们开展了一项众包实验，336名参与者在决定美国国防支出时，与中立型或两种价值导向型聊天机器人交互。在单一政策领域且内容受控的条件下，接触价值框架型机器人的参与者其预算选择显著偏离中立对照组。当框架与个人价值观不符时，部分参与者反而强化原有立场，揭示出一种可复现的“反弹效应”，此前文献认为该现象罕见。结果表明，仅靠价值框架即可降低大模型被滥用的门槛，带来不同于显性偏见或虚假信息的独特风险，并为应对虚假信息提供了新视角。
原文摘要 · Abstract (English)
Similar to social media bots that shape public opinion, healthcare and financial decisions, LLM-based ChatBots like ChatGPT can persuade users to alter their behavior. Unlike prior work that persuades via overt-partisan bias or misinformation, we test whether framing alone suffices. We conducted a crowdsourced study, where 336 participants interacted with a neutral or one of two value-framed ChatBots while deciding to alter US defense spending. In this single policy domain with controlled content, participants exposed to value-framed ChatBots significantly changed their budget choices relative to the neutral control. When the frame misaligned with their values, some participants reinforced their original preference, revealing a potentially replicable backfire effect, originally considered rare in the literature. These findings suggest that value-framing alone lowers the barrier for manipulative uses of LLMs, revealing risks distinct from overt bias or misinformation, and clarifying risks to countering misinformation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。