Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models

You Li, Jinhui Yin, Yuming Lin


Abstract
Pretrained language models are expected to effectively map input text to a set of vectors while preserving the inherent relationships within the text. Consequently, designing a white-box model to compute metrics that reflect the presence of specific internal relations in these vectors has become a common approach for post-hoc interpretability analysis of pretrained language models. However, achieving interpretability in white-box models and ensuring the rigor of metric computation becomes challenging when the source model lacks inherent interpretability. Therefore, in this paper, we discuss striking a balance in this trade-off and propose a novel line to constructing metrics for understanding the mechanisms of pretrained language models. We have specifically designed a family of metrics along this line of investigation, and the model used to compute these metrics is referred to as the tree topological probe. We conducted measurements on BERT-large by using these metrics. Based on the experimental results, we propose a speculation regarding the working mechanism of BERT-like pretrained language models, as well as a strategy for enhancing fine-tuning performance by leveraging the topological probe to improve specific submodules.
Anthology ID:
2023.findings-emnlp.894
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13399–13412
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.894
DOI:
10.18653/v1/2023.findings-emnlp.894
Bibkey:
Cite (ACL):
You Li, Jinhui Yin, and Yuming Lin. 2023. Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 13399–13412, Singapore. Association for Computational Linguistics.
Cite (Informal):
Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models (Li et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.findings-emnlp.894.pdf