Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons

by   Yuheng Chen, et al.

Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in multilingual PLMs, and introduces the Architecture-adapted Multilingual Integrated Gradients method, which successfully localizes knowledge neurons more precisely compared to current methods, and is more universal across various architectures and languages. Moreover, we conduct an in-depth exploration of knowledge neurons, leading to the following two important discoveries: (1) The discovery of Language-Independent Knowledge Neurons, which store factual knowledge in a form that transcends language. We design cross-lingual knowledge editing experiments, demonstrating that the PLMs can accomplish this task based on language-independent neurons; (2) The discovery of Degenerate Knowledge Neurons, a novel type of neuron showing that different knowledge neurons can store the same fact. Its property of functional overlap endows the PLMs with a robust mastery of factual knowledge. We design fact-checking experiments, proving that the degenerate knowledge neurons can help the PLMs to detect wrong facts. Experiments corroborate these findings, shedding light on the mechanisms of factual knowledge storage in multilingual PLMs, and contribute valuable insights to the field. The source code will be made publicly available for further research.


page 1

page 2

page 3

page 4


Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models

The success of multilingual pre-trained models is underpinned by their a...

Locating and Editing Factual Knowledge in GPT

We investigate the mechanisms underlying factual knowledge recall in aut...

Knowledge Neurons in Pretrained Transformers

Large-scale pretrained language models are surprisingly good at recallin...

Finding Skill Neurons in Pre-trained Transformer-based Language Models

Transformer-based pre-trained language models have demonstrated superior...

Adapters for Enhanced Modeling of Multilingual Knowledge and Text

Large language models appear to learn facts from the large text corpora ...

Language Anisotropic Cross-Lingual Model Editing

Pre-trained language models learn large amounts of knowledge from their ...

Finding patterns in Knowledge Attribution for Transformers

We analyze the Knowledge Neurons framework for the attribution of factua...

Please sign up or login with your details

Forgot password? Click here to reset