[4Xin2] Poster session 2

[4Xin2-94] Analysis of the Topic Transition Graph Using Word Association based on Large Language Model

〇Kai Yoshida^1,2, Seiya Kawano^2,1, Koichiro Yoshino^2,1 (1.Nara Institute of Science and Technology, 2.RIKEN Guardian Robot Project)

Keywords:Dialogu System, Topic Transition, Large Language Model

Dialog systems need not only to generate natural responses in the dialogue context but also to transit the topic naturally, which the user is more interested in.
In this study, we propose the method for constructing a topic transition graph generated from word association based on large language model, which can naturally transit the dialogue topic according to the user's preference.
We evaluate the topic transition graphs generated from several methods for investigating better topic transition of dialogue systems.