政治偏见认知削弱大模型说服力，用户更抗拒被
Perceived Political Bias in LLMs Reduces Persuasive Abilities
- 通过预注册实验测试用户对大模型政治偏见的感知影响
- 感知偏见使说服力下降28%，用户反驳更多且更不开放
- 适合关注AI在公共议题中可信度与政治传播的研究者
对话式AI被提议作为纠正公众误解和传播虚假信息的可扩展方式。然而，其有效性可能取决于用户对其政治中立性的感知。随着大模型卷入政党冲突，精英阶层日益将其描绘为意识形态倾向性工具。我们通过一项美国预注册调查实验（N=2144）检验此类信誉攻击是否削弱基于大模型的说服效果。参与者与ChatGPT展开三轮关于个人持有的经济政策误解的对话。相较于中立对照组，接收到提示大模型偏向对方政党的简短信息后，说服力下降28%。转录文本分析表明，警告改变了互动模式：受访者更倾向于反驳，且表现出更低的接纳度。这些发现表明，对话式AI的说服力具有政治依赖性，受限于用户对其党派倾向性的感知。
原文摘要 · Abstract (English)
Conversational AI has been proposed as a scalable way to correct public misconceptions and spread misinformation. Yet its effectiveness may depend on perceptions of its political neutrality. As LLMs enter partisan conflict, elites increasingly portray them as ideologically aligned. We test whether these credibility attacks reduce LLM-based persuasion. In a preregistered U.S. survey experiment (N=2144), participants completed a three-round conversation with ChatGPT about a personally held economic policy misconception. Compared to a neutral control, a short message indicating that the LLM was biased against the respondent's party attenuated persuasion by 28%. Transcript analysis indicates that the warnings alter the interaction: respondents push back more and engage less receptively. These findings suggest that the persuasive impact of conversational AI is politically contingent, constrained by perceptions of partisan alignment.
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。