[3Xin2] Poster session 1

[3Xin2-74] An attempt to translate natural language to AIWolf protocols using a multilingual

〇Akihiro Mikami¹, Takashi Otsuki² (1.Yamagata University Graduate School of Science and Engineering Department of Information Electronics, 2.Yamagata University Graduate School of Science and Engineering)

Keywords:machine translation, AIWolf, natural language, AIWolf protocol, translation model

In the natural language division of 2023 International AIWolf Competition, many AI agents using LLM-based generative AI played werewolf games with more natural conversation than before. However, there are many inconsistencies between statements and between statements and actions. One possible improvement method is an architecture in which a protocol agent capable of consistent behavior and utterance wrapped in a natural language I/O part which mutually converts between AIWolf protocol and natural language.In this study, we attempt to translate AIWolf agents' Japanese utterances into AIWolf protocols by fine-tuning a multilingual translation model. As a result, it is shown that the obtained model is able to translate simple and short sentences into appropriate protocols, but is unable to convert complex and long sentences.