Information Access in the Era of Generative AI

Erscheinungsjahr 2025
ISBN: 978-3-031-73149-5
Verlag: Springer

Buch, Englisch, Band 51, 248 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 400 g

Reihe: The Information Retrieval Series

Generative Artificial Intelligence (GenAI) has emerged as a groundbreaking technology that promises to revolutionize many industries as well as people’s personal and professional lives. This book discusses GenAI and its role in information access - often referred to as Generative Information Retrieval (GenIR) - or more broadly, information interaction.

The role of GenAI in information access is complex and dynamic, with many dimensions. To address this, following a brief introduction to GenAI and GenIR, the remainder of the book provides eight chapters, each targeting a different dimension or sub-topic. These cover foundations of GenIR, interactions with GenIR systems, adapting them to users, tasks, and scenarios, improving them based on user feedback, GenIR evaluation, the sociotechnical implications of GenAI for information access, recommendations within GenIR, and the future of information access with GenIR.

The book is targeted at graduate students and researchers interested in issues of information retrieval, access, and interactions, as well as applications of GenAI in various informational contexts. While some of the parts assume prior background in IR or AI, most others do not, making this book suitable for adoption in various classes as a primary source or as a supplementary material.

Zielgruppe

Research

Autoren/Hrsg.

White, Ryen W.

Shah, Chirag

Fachgebiete

• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Data Warehouse
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz
• Mathematik | Informatik EDV | Informatik Angewandte Informatik
• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Information Retrieval

Inhaltsverzeichnis

1. Introduction.- 2. Foundations of Generative IR.- 3. Interactions With Generative IR Systems.- 4. Adapting Generative IR Systems to Users, Tasks, and Scenarios.- 5. Improving Generative IR Systems Based on User Feedback.- 6. Generative IR Evaluation.- 7. Sociotechnical Implications of Generative AI for Information Access.- 8. Recommendation in the Era of Generative AI.- 9. Designing for the Future of Information Access with Generative IR.

Über Autor(innen)

Ryen W. White is a Research Scientist, General Manager, and Deputy Lab Director of Microsoft Research in Redmond, WA, USA. He is also an Affiliate Professor at the University of Washington. Ryen’s research takes a user- and task-centric view on Artificial Intelligence (AI), with a focus on search and assistance. Technology derived from his and his team’s research has significantly improved key business metrics in many Microsoft products, including Bing, Office, and Windows. Ryen is a Fellow of the Association for Computing Machinery (ACM) and of the British Computer Society. He has published over 300 articles and has received over 65 patents on search and related areas, including significant work on mining and modeling search activity at scale. Ryen has received over 20 awards for his technical contributions, including three ACM Special Interest Group on Information Retrieval (SIGIR) Best Paper awards and two SIGIR Test of Time awards. He has received the Karen Spärck Jones Award (2014) and the Tony Kent Strix Award (2022) for outstanding contributions to search. Ryen is one of a handful of scientists who have been inducted into both the SIGIR and the SIGCHI Academies. He currently serves as Editor-in-Chief of ACM Transactions on the Web and as SIGIR Vice Chair.

Chirag Shah is Professor in the Information School (iSchool) at the University of Washington in Seattle, WA, USA. He is also Adjunct Professor with the Paul G. Allen School of Computer Science & Engineering as well as Human Centered Design & Engineering (HCDE). He is the Founding Director for InfoSeeking Lab and Founding Co-Director of Center for Responsibility in AI Systems & Experiences (RAISE). His research focuses on building, auditing, and correcting intelligent information access systems. In addition to creating AI-driven information access systems that provide more personalized reactive and proactive recommendations, he is also focusing on making such systems transparent, fair, and free of biases. Shah is a Distinguished Member of ACM and ASIS&T. He is the recipient of the Karen Spärck Jones Award (2019) and ASIS&T Research in Information Science Award (2024). He has published nearly 200 peer-reviewed articles and authored seven books, including textbooks on data science and machine learning. He also works closely with industrial research labs on cutting-edge problems, typically as a visiting researcher. The most recent engagements include Amazon, Getty Images, Microsoft Research, and Spotify. He currently serves as Editor-in-Chief of Information Matters, published by ASIS&T.