通过大语言模型生成的推荐解释推动可持续选择
Nudging Sustainable Choices through LLM-Generated Recommendation Explanations
浏览论文内容
中文总结 AI 辅助
研究通过大语言模型生成推荐解释，探讨不同可持续性信息框架对用户选择和认知的影响。在速溶咖啡和酒店预订领域进行随机研究，发现框架构建或援引规范能增加可持续选择，虽认知与行为有差异，但为社会公益干预提供实践方向。
中文摘要 AI 辅助
推荐系统在日常消费中发挥作用，是鼓励可持续选择的有前景渠道。先前研究表明解释会影响用户对推荐的看法并助于更明智决策。本文认为解释可作为行为助推，在选择时刻突出可持续性信息。研究不同行为框架的可持续性信息在推荐解释中如何影响用户选择和认知。利用生成式人工智能，依据助推理论生成可持续性感知解释并通过人工评估和大语言模型审核验证。在此基础上，在速溶咖啡（低参与度领域）和酒店预订（高参与度领域）进行两项随机研究（\(N = 529\)），让参与者在有这些解释的偏好匹配推荐中选择。结果显示，在两个领域中，仅在解释中披露可持续性信息不会改变选择，而对该信息进行框架构建或援引描述性社会规范会显著增加可持续选择并简化决策。值得注意的是，认知和行为存在差异，单纯披露虽提高了解释评价，但未转化为更可持续的选择行为。研究展示了大语言模型如何大规模生成基于理论的解释，为基于解释的社会公益干预提供了实践方向。最后讨论了对生成式人工智能适应性解释设计的启示。
英文摘要
Recommender systems mediate everyday consumption, offering a promising channel for encouraging sustainable choices. Prior research shows that explanations influence users' perceptions of recommendations and can support more informed decisions. We argue that explanations can also serve as behavioral nudges by foregrounding sustainability information at the moment of choice. This study investigates how different behavioral framings of sustainability information in recommendation explanations affect user choices and perceptions. Using generative AI, we generate sustainability-aware explanations by drawing on nudge theory and validate them through human evaluation and LLM-as-a-judge audits. Building on this foundation, we conduct two randomized studies (N = 529) in a low involvement domain (instant coffee) and a high involvement domain (hotel bookings), in which participants choose among preference matched recommendations accompanied by these explanations. Our results show that, across both domains, merely disclosing sustainability information in explanations does not change choices, whereas framing that information or invoking a descriptive social norm significantly increases sustainable selections and eases decision-making. Notably, perception and behavior diverge, as plain disclosure improves explanation evaluations without translating into more sustainable selection behavior. Our work demonstrates how LLMs can generate theory-grounded explanations at scale, pointing toward practical explanation-based interventions for social good. We conclude by discussing implications for adaptive explanation design with generative AI.
发表机构
- Paderborn University（帕德博恩大学）
- University of Klagenfurt（克拉根福大学）
机构由 AI 辅助整理，请以论文原文为准。
