GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?

Dayoon Ko, Jinyoung Kim, Hahyeon Choi, Gunhee Kim


Abstract
In the real world, knowledge is constantly evolving, which can render existing knowledge-based datasets outdated. This unreliability highlights the critical need for continuous updates to ensure both accuracy and relevance in knowledge-intensive tasks. To address this, we propose GrowOVER-QA and GrowOVER-Dialogue, dynamic open-domain QA and dialogue benchmarks that undergo a continuous cycle of updates, keeping pace with the rapid evolution of knowledge. Our research indicates that retrieval-augmented language models (RaLMs) struggle with knowledge that has not been trained on or recently updated. Consequently, we introduce a novel retrieval-interactive language model framework, where the language model evaluates and reflects on its answers for further re-retrieval. Our exhaustive experiments demonstrate that our training-free framework significantly improves upon existing methods, performing comparably to or even surpassing continuously trained language models.
Anthology ID:
2024.acl-long.181
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3282–3308
Language:
URL:
https://aclanthology.org/2024.acl-long.181
DOI:
10.18653/v1/2024.acl-long.181
Bibkey:
Cite (ACL):
Dayoon Ko, Jinyoung Kim, Hahyeon Choi, and Gunhee Kim. 2024. GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3282–3308, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge? (Ko et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.181.pdf