本文探讨了在在线广告系统领域利用 Large Language Models(LLM,大语言模型)的潜力。我们提出了一个用于 LLM 广告的通用框架,由修改、出价、预测和拍卖模块组成。文中介绍了每个模块的不同设计考量,并基于维持可持续系统所需的关键期望属性,对这些设计选择进行了评估和讨论。文章还提出了关于实用性、效率和实施挑战的进一步基础性问题,以供未来研究。最后,我们阐述了近期面向 LLM 的机制设计方法如何能够被纳入我们的统一视角。
英文摘要:
This paper explores the potential for leveraging Large Language Models (LLM) in the realm of online advertising systems. We introduce a general framework for LLM advertisement, consisting of modification, bidding, prediction, and auction modules. Different design considerations for each module are presented. These design choices are evaluated and discussed based on essential desiderata required to maintain a sustainable system. Further fundamental questions regarding practicality, efficiency, and implementation challenges are raised for future research. Finally, we exposit how recent approaches on mechanism design for LLM can be framed in our unified perspective.
Always Lurking: Understanding and Mitigating Bias in Online Human Trafficking Detection
NASA Jet Propulsion Laboratory(美国国家航空航天局喷气推进实验室);California Institute of Technology(加州理工学院);Information Sciences Institute(信息科学研究所);University of Southern California(南加利福尼亚大学);Carnegie Mellon University(卡内基梅隆大学)
InstaSynth: Opportunities and Challenges in Generating Synthetic Instagram Data with ChatGPT for Sponsored Content Detection
Utrecht University(乌得勒支大学);University College Maastricht, Maastricht University(马斯特里赫特大学马斯特里赫特大学学院);Indira Gandhi Delhi Technical University for Women(英迪拉·甘地德里女子技术大学)