Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models

Yujin Kim, Jaehong Yoon, Seonghyeon Ye, Sangmin Bae, Namgyu Ho, Sung Ju Hwang, Se-Young Yun


Abstract
The dynamic nature of knowledge in an ever-changing world presents challenges for language models trained on static data; the model in the real world often requires not only acquiring new knowledge but also overwriting outdated information into updated ones. To study the ability of language models for these time-dependent dynamics in human language, we introduce a novel task, EvolvingQA, a temporally evolving question-answering benchmark designed for training and evaluating LMs on an evolving Wikipedia database. The construction of EvolvingQA is automated with our pipeline using large language models. We uncover that existing continual learning baselines suffer from updating and removing outdated knowledge. Our analysis suggests that models fail to rectify knowledge due to small weight gradients. In addition, we elucidate that language models particularly struggle to reflect the change of numerical or temporal information. Our work aims to model the dynamic nature of real-world information, suggesting faithful evaluations of the evolution-adaptability of language models. Our data construction code and dataset files are available at https://github.com/kimyuji/EvolvingQA_benchmark.
Anthology ID:
2024.naacl-long.302
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5401–5415
Language:
URL:
https://aclanthology.org/2024.naacl-long.302
DOI:
10.18653/v1/2024.naacl-long.302
Bibkey:
Cite (ACL):
Yujin Kim, Jaehong Yoon, Seonghyeon Ye, Sangmin Bae, Namgyu Ho, Sung Ju Hwang, and Se-Young Yun. 2024. Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5401–5415, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Carpe diem: On the Evaluation of World Knowledge in Lifelong Language Models (Kim et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.302.pdf