时间：2024年6月14日（周五）14:00
地点：东南大学九龙湖校区计算机楼513室
报告人：Prof. Charles L.A. Clarke 加拿大滑铁卢大学
报告人简介：Charles Clarke is a Professor in the School of Computer Science and an Associate Dean for Innovation and Entrepreneurship at the University of Waterloo, Canada. His research focuses on data intensive tasks involving human language data, including search, ranking, and question answering. Clarke is an ACM Distinguished Scientist and leading member of the search and information retrieval community. His h-index is as high as 51. He served as the Co-Editor-in-Chief of the Information Retrieval.
报告摘要：Search, recommendation, and other information retrieval (IR) systems have traditionally been evaluated with a combination of implicit feedback from user interactions, explicit user feedback, and paid assessment by human labellers. Over the past year, both academic researchers and commercial services have begun to employ large language models to replace and augment human assessment for IR evaluation. Over the same period, generative information retrieval (Gen-IR) systems and retrieval augmented generation (RAG) systems have emerged as alternatives to traditional IR systems. The role of IR evaluation has always been to answer questions like, “Is this system better than that one?” and “Does this search result satisfy the searcher’s information need?” In a world where large language models can outperform human labellers on basic relevance assessment tasks, and where the results of a search are used only as input to a generative system, how do we answer these questions, and are these even the right questions to ask? While we can now build IR systems that we could only dream about a few years ago, we still need to know if changes to a system reflect genuine benefits to its users. In this talk, I will survey the research landscape as it exists in June 2024 and outline recent results from my lab that point to directions forward.
