AI劝说AI比劝说真人更有效，揭示了对话AI在环保行为干预中的潜力与局限。
AI persuading AI vs AI persuading Humans: LLMs' Differential Effectiveness in Promoting Pro-Environmental Behavior
- 用真实、模拟和虚拟用户对比，测试LLM对环保行为的影响
- 虚拟和模拟用户受劝说后态度变化显著，真人反应微弱
- 适合研究者预评估环保对话AI，但需更多真实人类实验验证
应对气候变化亟需推动环保行为（PEB），但意识难以转化为行动。本文探讨大语言模型（LLMs）作为促进PEB的工具，通过3,200名参与者（真实人类n=1,200，基于真实数据模拟的人类n=1,200，完全合成角色n=1,200）进行实验。所有参与者面对个性化或标准聊天机器人，或静态陈述，采用四种说服策略（道德基础、未来自我连续性、行动导向、“自由发挥”由LLM自选）。结果显示“合成劝说悖论”：合成与模拟主体的环保行为立场显著改变，而真实人类反应几乎不变。模拟参与者虽能较好复现人类趋势，但仍高估干预效果。这表明LLM可用于预评估环保干预，但预测真实行为存在局限。研究呼吁改进合成建模，并开展更长期、更大规模的人类实验，以实现对话AI与可持续成果的真正对齐。
原文摘要 · Abstract (English)
Pro-environmental behavior (PEB) is vital to combat climate change, yet turning awareness into intention and action remains elusive. We explore large language models (LLMs) as tools to promote PEB, comparing their impact across 3,200 participants: real humans (n=1,200), simulated humans based on actual participant data (n=1,200), and fully synthetic personas (n=1,200). All three participant groups faced personalized or standard chatbots, or static statements, employing four persuasion strategies (moral foundations, future self-continuity, action orientation, or "freestyle" chosen by the LLM). Results reveal a "synthetic persuasion paradox": synthetic and simulated agents significantly affect their post-intervention PEB stance, while human responses barely shift. Simulated participants better approximate human trends but still overestimate effects. This disconnect underscores LLM's potential for pre-evaluating PEB interventions but warns of its limits in predicting real-world behavior. We call for refined synthetic modeling and sustained and extended human trials to align conversational AI's promise with tangible sustainability outcomes.
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。