[3Win5] Poster session 3

[3Win5-23] Understanding and Processing of Japanese Polite and Non-Polite Language in Generative Models

〇Ryuichi Watanabe¹ (1.Kyoto University)

Keywords:AI, NLP, transformer

In this paper, we aim to clarify how generative models, including GPT-2, understand and process Japanese polite and non-polite sentences by analyzing “keigo neurons,” which respond strongly to each of these forms. Specifically, after identifying the keigo neurons that correspond to polite and non-polite expressions, we evaluate their performance as binary classifiers that distinguish between polite and non-polite sentences, and investigate their behavior when input sentences are fed into the model. Additionally, we conduct supplementary experiments in which we manipulate the activation values of these keigo neurons before generating text with the model. Our findings provide insights into how the model conceptualizes polite and non-polite language and offer suggestions for improving language-specialized models.