会回应的广告：将个性化广告注入LLM聊天机器人的影响与感知
Ads that Talk Back: Implications and Perceptions of Injecting Personalized Advertising into LLM Chatbots
AI总结：
本研究通过实验证明，将个性化广告注入LLM响应仅轻微影响性能，且用户难以察觉甚至偏好隐藏广告，并开发了广告数据集与开源模型Phi-4-Ads。
摘要：
大型语言模型（LLM）的最新进展使得创建高效聊天机器人成为可能。然而，广泛部署LLM的计算成本引发了对盈利能力的质疑。公司已提出探索基于广告的收入流以实现LLM的货币化，这可能使LLM成为新的事实上的广告平台。本文通过一项涉及179名参与者的受试者间实验，研究将LLM广告个性化到个体用户的影响。我们开发了一个聊天机器人，受AI公司类似尝试的启发，将个性化产品广告嵌入LLM响应中。我们基准测试的评估显示，广告注入仅轻微影响LLM性能，尤其是响应可取性。结果显示，参与者难以察觉广告，甚至更喜欢带有隐藏广告的LLM响应。参与者没有点击我们的广告披露，而是尝试使用自然语言查询更改其广告设置。我们创建了一个广告数据集和一个开源LLM Phi-4-Ads，该模型经过微调以提供广告并灵活适应用户偏好。
英文摘要：
Recent advances in large language models (LLMs) have enabled the creation of highly effective chatbots. However, the compute costs of widely deploying LLMs have raised questions about profitability. Companies have proposed exploring ad-based revenue streams for monetizing LLMs, which could serve as the new de facto platform for advertising. This paper investigates the implications of personalizing LLM advertisements to individual users via a between-subjects experiment with 179 participants. We developed a chatbot that embeds personalized product advertisements within LLM responses, inspired by similar forays by AI companies. The evaluation of our benchmarks showed that ad injection only slightly impacted LLM performance, particularly response desirability. Results revealed that participants struggled to detect ads, and even preferred LLM responses with hidden advertisements. Rather than clicking on our advertising disclosure, participants tried changing their advertising settings using natural language queries. We created an advertising dataset and an open-source LLM, Phi-4-Ads, fine-tuned to serve ads and flexibly adapt to user preferences.
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。
