Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge
Daniel Tamayo, Aitor Gonzalez-Agirre, Javier Hernando, Marta Villegas
Abstract
Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effectiveness of existing knowledge editing methods across languages and delving into the role of attention mechanisms in this process. Drawing from the insights gained, we propose Mass-Editing Memory with Attention in Transformers (MEMAT), a method that achieves significant improvements in all metrics while requiring minimal parameter modifications. MEMAT delivers a remarkable 10% increase in magnitude metrics, benefits languages not included in the training data and also demonstrates a high degree of portability. Our code and data are at https://github.com/dtamayo-nlp/MEMAT.
BibTeX
@inproceedings{mela-etal-2024-mass,
title = "Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge",
author = "Tamayo, Daniel and
Gonzalez-Agirre, Aitor and
Hernando, Javier and
Villegas, Marta",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.347/",
doi = "10.18653/v1/2024.findings-acl.347",
pages = "5831--5847"
}