arXiv 2604.169352026-04-18cs.AIcs.CYcs.HCcs.LGcs.SI

LLMs只能通过信任AI和情感诉求说服心理上易受影响的人群在社会问题上的观点，尽管存在逻辑谬误

LLMs can persuade only psychologically susceptible humans on societal issues, via trust in AI and emotional appeals, amid logical fallacies

organization= CogNosco Lab, Department of Psychology；Cognitive Science, University of Trento , city= Rovereto , country= Italy；organization= Institute of Information Science；Technologies ``Alessandro Faedo", National Research Council , country= Italy；organization= Thomas Lord Department of Computer Science, University of Southern California , city= Los Angeles , state= California , country= USA；organization= Department of Sociology；Social Research, University of Trento , city= Trento , country= Italy；organization= Centre for Behavioural；Implementation Sciences in Medicine (BISI), National University of Singapore , city= Singapore , country= Singapore

Alexis Carrillo, Salvatore Citraro, Ali Aghazhadeh Ardebili, Enrique Taietta, Giulio Rossetti, Emilio Ferrara, Giuseppe Alessandro Veltri, Massimo Stella

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文通过Talk2AI框架研究LLM在时间演变的心理框架下对社会议题的说服力，发现人类对AI的可信度和情感诉求影响其观点变化，同时揭示了逻辑谬误在说服过程中的作用。

摘要：

稀缺的纵向证据研究了LLM的说服力和人性在时间演变的心理框架下的表现。我们介绍了Talk2AI，一个纵向框架，用于量化LLM在争议性社会议题上的说服力的psycho-social、推理和情感维度。在四维纵向设置中，Talk2AI的770名参与者与四个领先的LLM在气候变化、社交媒体虚假信息和数学焦虑等话题上进行了结构化对话。这产生了3,080次对话，共60,000次回合。每次波段后，参与者报告了对初始话题立场的信念、感知观点变化、LLM的感知人性、自我捐赠给该话题以及文本解释。反馈时间序列显示了信念的纵向惯性，表明一些人类在反复接触AI生成论点后仍锚定于初始观点。有趣的是，NLP分析显示，人类和LLM在每6次对话中都依赖于谬误推理，反驳了LLM作为优越系统的刻板印象。LLM的感知人性最可从社会人口统计、心理和参与特征（R²=0.44）学习，其次是观点变化（R²=0.34）、信念（R²=0.26）和个人投入（R²=0.24）。关键的是，可解释AI（XAI）表明：（i）存在更易受LLM影响观点的个体；（ii）对LLM说服的心理易感性包括对LLM的更多信任、更同意和外向性以及更高的认知需求。多宇宙方法与混合效应模型确认了XAI的结果，同时伴随着显著的个体差异。Talk2AI提供了一个扎根的框架和证据，用于检测GenAI如何通过多个psycho-social路径在AI-人类数字平台中影响人类观点。

英文摘要：

Scarce longitudinal evidence examines LLMs' persuasiveness and humanness along time-evolving psychological frameworks. We introduce Talk2AI, a longitudinal framework quantifying psycho-social, reasoning and affective dimensions of LLMs' persuasiveness about polarizing societal topics. In a four-way longitudinal setup, Talk2AI's 770 participants engaged in structured conversations with one of four leading LLMs on topics like climate change, social media misinformation, and math anxiety. This produced 3,080 conversations over 60,000 turns. After each wave, participants reported conviction in their initial topic stance, perceived opinion change, LLM's perceived humanness, a self-donation to the topic and a textual explanation. Feedback time series showed longitudinal inertia in convictions, indicating some human anchoring to initial opinions even after repeated exposure to AI-generated arguments. Interestingly, NLP analyses revealed that both humans and LLMs relied on fallacious reasoning in 1 conversational quip every 6, countering the ``LLMs as superior systems" stereotype behind LLMs' cognitive surrender. LLMs' perceived humanness was most learnable from sociodemographic, psychological and engagement features ($R^2=0.44$), followed by opinion change ($R^2=0.34$), conviction ($R^2=0.26$) and personal endowment ($R^2=0.24$). Crucially, explainable AI (XAI) indicated: (i) the presence of individuals more susceptible to LLM-based opinion changes; (ii) psychological susceptibility to LLM-convincing consisted of having more trust in LLMs, being more agreeable and extraverted and with a higher need for cognition. A multiverse approach with mixed-effects models confirmed XAI results, alongside strong individual differences. Talk2AI provides a grounded framework and evidence for detecting how GenAI can influence human opinions via multiple psycho-social pathways in AI-human digital platforms.

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。