大语言模型作为对话式电影推荐系统：一项用户研究
Large Language Models as Conversational Movie Recommenders: A User Study
AI总结：
本文通过160名用户的在线实验研究大语言模型在对话式电影推荐中的表现，发现其可解释性强但个性化、多样性和信任不足，且提供个人背景和示例是获得高质量推荐的关键。
摘要：
本文通过一项在线实地实验，从用户视角探讨使用大语言模型（LLMs）进行个性化电影推荐的有效性。我们的研究结合了被试间提示与历史消费评估，以及被试内推荐场景评价。通过分析160名活跃用户的对话和调查回复数据，我们发现LLMs提供了较强的推荐可解释性，但在整体个性化、多样性和用户信任方面存在不足。我们的结果还表明，不同的个性化提示技术对用户感知的推荐质量没有显著影响，而用户观看过的电影数量则发挥了更显著的作用。此外，LLMs在推荐小众或冷门电影方面表现出更强的能力。通过定性分析，我们识别了与积极和消极用户互动体验相关的关键对话模式，并得出结论：提供个人背景和示例对于从LLMs获得高质量推荐至关重要。
英文摘要：
This paper explores the effectiveness of using large language models (LLMs) for personalized movie recommendations from users' perspectives in an online field experiment. Our study involves a combination of between-subject prompt and historic consumption assessments, along with within-subject recommendation scenario evaluations. By examining conversation and survey response data from 160 active users, we find that LLMs offer strong recommendation explainability but lack overall personalization, diversity, and user trust. Our results also indicate that different personalized prompting techniques do not significantly affect user-perceived recommendation quality, but the number of movies a user has watched plays a more significant role. Furthermore, LLMs show a greater ability to recommend lesser-known or niche movies. Through qualitative analysis, we identify key conversational patterns linked to positive and negative user interaction experiences and conclude that providing personal context and examples is crucial for obtaining high-quality recommendations from LLMs.
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。
