Discovering Knowledge-Critical Subnetworks in Pretrained Language Models

Deniz Bayazit, Negar Foroutan, Zeming Chen, Gail Weiss, Antoine Bosselut


Abstract
Pretrained language models (LMs) encode implicit representations of knowledge in their parameters. However, localizing these representations and disentangling them from each other remains an open problem. In this work, we investigate whether pretrained language models contain various *knowledge-critical* subnetworks: particular sparse computational subgraphs that can, if removed, precisely suppress specific knowledge the model has memorized. We propose a multi-objective differentiable masking scheme that can be applied to both weights and neurons to discover such subnetworks and show that we can use them to precisely remove specific knowledge from models while minimizing adverse effects on the behavior of the original model. We demonstrate our method on multiple GPT2 variants, uncovering highly sparse subnetworks (98%+ sparsity) that are critical for expressing specific collections of relational knowledge. When these subnetworks are removed, the remaining network maintains most of its initial abilities but struggles to represent the suppressed knowledge.
Anthology ID:
2024.emnlp-main.376
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:
6549–6583
Language:
URL:
https://aclanthology.org/2024.emnlp-main.376
DOI:
10.18653/v1/2024.emnlp-main.376
Bibkey:
Cite (ACL):
Deniz Bayazit, Negar Foroutan, Zeming Chen, Gail Weiss, and Antoine Bosselut. 2024. Discovering Knowledge-Critical Subnetworks in Pretrained Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 6549–6583, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Discovering Knowledge-Critical Subnetworks in Pretrained Language Models (Bayazit et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.376.pdf