大语言模型能够有效地说服人们相信阴谋论
Large language models can effectively convince people to believe conspiracies
AI总结:
研究大语言模型能否有效说服人们相信阴谋论,通过四项实验发现其既能增加也能降低阴谋信念,反驳效果更佳,特定提示可降低支持阴谋论有效性,还存在信息分享上的真理不对称,有潜在技术方案减轻风险。
摘要:
大语言模型(LLMs)在多种情境下已被证明具有说服力。但尚不清楚这种说服力是否有利于准确性,或者不良行为者是否能同样轻易地利用大语言模型来传播错误信念。在此,我们通过四项实验来研究这个问题,3996名美国参与者与按要求反驳或支持阴谋论的大语言模型讨论他们不确定的阴谋论。在几个前沿模型中,我们没有发现真理优势的一致证据:大语言模型既能大幅增加也能降低平均阴谋信念,支持阴谋论的参与者认为大语言模型更有信息价值和协作性,且对人工智能的信任度更高。不过,反驳能引起信念的更大变化,后续的纠正能够扭转支持阴谋论的效果。此外,简单地促使模型只提供准确信息会大幅降低支持阴谋论的有效性,一个强大的前沿模型几乎完全拒绝支持阴谋论。最后,在信息分享方面存在明显的真理不对称:反驳对参与者撰写的模拟社交媒体帖子有很大的积极影响,而支持阴谋论则几乎没有效果。总体而言,我们的研究结果表明,人们并非天生就更不易受误导性人工智能的影响,而不是信息性人工智能的影响,但存在潜在的技术解决方案来减轻这种风险。
英文摘要:
Large language models (LLMs) have been shown to be persuasive across a variety of contexts. But it remains unclear whether this persuasive power advantages accuracy, or if bad actors can just as easily use LLMs to promote misbeliefs. Here, we investigate this question across four experiments in which participants (N = 3996 Americans) discussed a conspiracy theory they were uncertain about with an LLM we instructed to either argue against ("debunking") or for ("bunking") that conspiracy. Across several frontier models (with standard guardrails but prompted to allow lying), we did not find consistent evidence of a truth advantage: the LLMs were able to both substantially increase and decrease average conspiracy belief, and participants in the bunking condition rated the LLM as more informative and collaborative, and reported greater trust in AI, than those who were in the debunking condition. More encouragingly, however, debunking induced more large changes in belief, and subsequent corrections were able to reverse the bunking effect. Furthermore, simply prompting the model to only provide accurate information dramatically reduced bunking effectiveness, and one powerful frontier model (GPT 5.2) almost entirely refused to promote conspiracies, suggesting that it is possible for the right guardrails to favor accurate beliefs. Finally, we did find a stark truth asymmetry in the context of information sharing: debunking had a large positive impact on mock social media posts composed by participants, while bunking had little effect. Overall, our findings show that people are not inherently less susceptible to AI that misleads than to AI that informs, but that potential technical solutions exist to mitigate this risk.
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。