Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?

Junyan Zhang, Yiming Huang, Shuliang Liu, Yubo Gao, Xuming Hu


Abstract
The rapid adoption of LLMs has overshadowed the potential advantages of traditional BERT-like models in text classification. This study challenges the prevailing “LLM-centric” trend by systematically comparing three category methods, *i.e.,* BERT-like models fine-tuning, LLM internal state utilization, and LLM zero-shot inference across six challenging datasets. Our findings reveal that BERT-like models often outperform LLMs. We further categorize datasets into three types, perform PCA and probing experiments, and identify task-specific model strengths: BERT-like models excel in pattern-driven tasks, while LLMs dominate those requiring deep semantics or world knowledge. Subsequently, we conducted experiments on a broader range of text classification tasks to demonstrate the generalizability of our findings. We further investigated how the relative performance of different models varies under different levels of data availability. Finally, based on these findings, we propose **TaMAS**, a fine-grained task selection strategy, advocating for a nuanced, task-driven approach over a one-size-fits-all reliance on LLMs. Code is available at [https://github.com/jyzhang2002/TaMAS-TextClass](https://github.com/jyzhang2002/TaMAS-TextClass).
Anthology ID:
2025.findings-emnlp.1033
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18980–18989
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.1033/
DOI:
Bibkey:
Cite (ACL):
Junyan Zhang, Yiming Huang, Shuliang Liu, Yubo Gao, and Xuming Hu. 2025. Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs?. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 18980–18989, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs? (Zhang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.1033.pdf
Checklist:
 2025.findings-emnlp.1033.checklist.pdf