On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
Takeshi Kojima, Itsuki Okimura, Yusuke Iwasawa, Hitomi Yanaka, Yutaka Matsuo
Abstract
Current decoder-based pre-trained language models (PLMs) successfully demonstrate multilingual capabilities. However, it is unclear how these models handle multilingualism.We analyze the neuron-level internal behavior of multilingual decoder-based PLMs, Specifically examining the existence of neurons that fire “uniquely for each language” within decoder-only multilingual PLMs.We analyze six languages: English, German, French, Spanish, Chinese, and Japanese, and show that language-specific neurons are unique, with a slight overlap (< 5%) between languages. These neurons are mainly distributed in the models’ first and last few layers. This trend remains consistent across languages and models.Additionally, we tamper with less than 1% of the total neurons in each model during inference and demonstrate that tampering with a few language-specific neurons drastically changes the probability of target language occurrence in text generation.
BibTeX
@inproceedings{kojima-etal-2024-multilingual,
title = "On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons",
author = "Kojima, Takeshi and
Okimura, Itsuki and
Iwasawa, Yusuke and
Yanaka, Hitomi and
Matsuo, Yutaka",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.384/",
doi = "10.18653/v1/2024.naacl-long.384",
pages = "6919--6971"
}