Editing Factual Knowledge in Language Models

Nicola De Cao, Wilker Aziz, Ivan Titov


Abstract
The factual knowledge acquired during pre-training and stored in the parameters of Language Models (LMs) can be useful in downstream tasks (e.g., question answering or textual inference). However, some facts can be incorrectly induced or become obsolete over time. We present KnowledgeEditor, a method which can be used to edit this knowledge and, thus, fix ‘bugs’ or unexpected predictions without the need for expensive re-training or fine-tuning. Besides being computationally efficient, KnowledgeEditordoes not require any modifications in LM pre-training (e.g., the use of meta-learning). In our approach, we train a hyper-network with constrained optimization to modify a fact without affecting the rest of the knowledge; the trained hyper-network is then used to predict the weight update at test time. We show KnowledgeEditor’s efficacy with two popular architectures and knowledge-intensive tasks: i) a BERT model fine-tuned for fact-checking, and ii) a sequence-to-sequence BART model for question answering. With our method, changing a prediction on the specific wording of a query tends to result in a consistent change in predictions also for its paraphrases. We show that this can be further encouraged by exploiting (e.g., automatically-generated) paraphrases during training. Interestingly, our hyper-network can be regarded as a ‘probe’ revealing which components need to be changed to manipulate factual knowledge; our analysis shows that the updates tend to be concentrated on a small subset of components. Source code available at https://github.com/nicola-decao/KnowledgeEditor
Anthology ID:
2021.emnlp-main.522
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6491–6506
Language:
URL:
https://aclanthology.org/2021.emnlp-main.522
DOI:
10.18653/v1/2021.emnlp-main.522
Bibkey:
Cite (ACL):
Nicola De Cao, Wilker Aziz, and Ivan Titov. 2021. Editing Factual Knowledge in Language Models. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6491–6506, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Editing Factual Knowledge in Language Models (De Cao et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2021.emnlp-main.522.pdf
Code
 nicola-decao/KnowledgeEditor +  additional community code