arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.27624cs.CLcs.AIcs.CYcs.HCcs.LG

映射LLMs在模仿人类性格特征、社会人口统计数据和社会媒体行为时如何辩论社会问题

Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior

CogNosco Lab, University of Trento, Department of Psychology and Cognitive Science(CogNosco实验室,特伦托大学心理学与认知科学系)

Ali Aghazadeh Ardebili, Massimo Stella

AI总结:

本文通过CDS数据集研究LLMs在不同社会和情境提示下生成的辩论内容变化,分析其社会议题立场和情感表达。

摘要:

大型语言模型(LLMs)能显著影响社会讨论,但研究LLM输出在受控社会和情境提示下变化的数据库仍较少。认知数字影子(CDS)是一个包含190,000条记录的合成语料库,支持对LLM生成讨论的分析。每个CDS记录由19个LLM之一生成,被提示模仿人类角色或AI助手角色。CDS包含关于疫苗/医疗、社交媒体虚假信息、科学性别差距和STEM刻板印象的4个有争议的社会话题的LLM回应。角色条件记录编码17个社会人口统计和心理属性,提供数据链接LLM提示、语言、立场和推理。文本经过主题锚定验证,并可通过可解释NLP(如文本形式思维网络)支持情感分析。CDS通过聚合平台和用户友好的仪表板得到增强,使用户能够轻松、互动地比较不同角色、主题和模型之间的情感和语义框架。CDS提示框架支持未来对LLM偏见、社会敏感性和对齐性的审计。

英文摘要:

Large Language Models (LLMs) can strongly shape social discourse, yet datasets investigating how LLM outputs vary across controlled social and contextual prompting remain sparse. Cognitive Digital Shadows (CDS) is a 190,000-record synthetic corpus supporting analyses of LLM-generated discourse. Each CDS record is generated by one of 19 LLMs, prompted to shadow either a human persona or an AI-assistant role. CDS contains LLM responses on 4 controversial societal topics: vaccines/healthcare, social media disinformation, the gender gap in science, and STEM stereotypes. Persona-conditioned records encode 17 sociodemographic and psychological attributes, providing data linking LLMs' prompts, language, stances and reasoning. Texts are validated for topic anchoring and can support emotional analyses via interpretable NLP (e.g. textual forma mentis networks). CDS is enriched by a pooling platform with user-friendly dashboards, enabling easy, interactive group-level comparisons of emotional and semantic framing across personas, topics and models. The CDS prompting framework supports future audits of LLMs' bias, social sensitivity and alignment.

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。

↑