Model Editing for New Document Integration in Generative Information Retrieval

ACM Web Conference (WWW), pp. 1993–2003

Abstract

Generative retrieval (GR) reformulates the Information Retrieval (IR) task as the generation of document identifiers (docIDs). Despite its promise, existing GR models exhibit poor generalization to newly added documents, often failing to generate the correct docIDs. While incremental training offers a straightforward remedy, it is computationally expensive, resource-intensive, and prone to catastrophic forgetting, thereby limiting the scalability and practicality of GR.

Authors 9

1. Z C Zhang

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

2. Zihan Wang

   University of Amsterdam

   Affiliation as printed

   University of Amsterdam, Qingdao, China

3. Xinyu Ma

   Baidu (China)

   Affiliation as printed

   Baidu Inc., Beijing, China

4. Shuaiqiang Wang

   Baidu (China)

   Affiliation as printed

   Baidu Inc., Beijing, China

5. Dawei Yin

   Baidu (China)

   Affiliation as printed

   Baidu Inc., Beijing, China

6. Xin Xin

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

7. Pengjie Ren

   Shandong University

   Affiliation as printed

   Shandong University, Qingdao, China

8. Maarten de Rijke

   University of Amsterdam

   Affiliation as printed

   University of Amsterdam, Amsterdam, Netherlands

9. Zhaochun Ren Aachen

   Leiden University

   Affiliation as printed

   Leiden University, Leiden, Netherlands