Exploring the Practicality of Generative Retrieval on Dynamic Corpora

Chaeeun Kim, Soyoung Yoon, Hyunji Lee, Joel Jang, Sohee Yang, Minjoon Seo


Abstract
Benchmarking the performance of information retrieval (IR) is mostly conducted with a fixed set of documents (static corpora). However, in realistic scenarios, this is rarely the case and the documents to be retrieved are constantly updated and added. In this paper, we focus on Generative Retrievals (GR), which apply autoregressive language models to IR problems, and explore their adaptability and robustness in dynamic scenarios. We also conduct an extensive evaluation of computational and memory efficiency, crucial factors for real-world deployment of IR systems handling vast and ever-changing document collections. Our results on the StreamingQA benchmark demonstrate that GR is more adaptable to evolving knowledge (4–11%), robust in learning knowledge with temporal information, and efficient in terms of inference FLOPs (x2), indexing time (x6), and storage footprint (x4) compared to Dual Encoders (DE), which are commonly used in retrieval systems. Our paper highlights the potential of GR for future use in practical IR systems within dynamic environments.
Anthology ID:
2024.emnlp-main.755
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13616–13633
Language:
URL:
https://aclanthology.org/2024.emnlp-main.755
DOI:
10.18653/v1/2024.emnlp-main.755
Bibkey:
Cite (ACL):
Chaeeun Kim, Soyoung Yoon, Hyunji Lee, Joel Jang, Sohee Yang, and Minjoon Seo. 2024. Exploring the Practicality of Generative Retrieval on Dynamic Corpora. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13616–13633, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Exploring the Practicality of Generative Retrieval on Dynamic Corpora (Kim et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.755.pdf