Discovering Knowledge-Critical Subnetworks in Neural Language Models
Primary Area: visualization or interpretation of learned representations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: sparse subnetworks, knowledge graphs, interpretability
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
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 responsible for encoding specific knowledge the model has memorized. We propose a multi-objective differentiable weight masking scheme to discover these 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 language model. We demonstrate our method on multiple GPT2 variants, uncovering highly sparse subnetworks (98\%+) that are solely responsible for specific collections of relational knowledge. When these subnetworks are removed, the remaining network maintains most of its initial capacity (modeling language and other memorized relational knowledge) but struggles to express the removed knowledge, and suffers performance drops on examples needing this removed knowledge on downstream tasks after finetuning.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7241
Loading