Takeshi Ito


2024

pdf bib
AIWolfDial 2024: Summary of Natural Language Division of 6th International AIWolf Contest
Yoshinobu Kano | Yuto Sahashi | Neo Watanabe | Kaito Kagaminuma | Claus Aranha | Daisuke Katagami | Kei Harada | Michimasa Inaba | Takeshi Ito | Hirotaka Osawa | Takashi Otsuki | Fujio Toriumi
Proceedings of the 2nd International AIWolfDial Workshop

We held our 6th annual AIWolf international contest to automatically play the Werewolf game “Mafia”, where players try finding liars via conversations, aiming at promoting developments in creating agents of more natural conversations in higher level, such as longer contexts, personal relationships, semantics, pragmatics, and logics, revealing the capabilities and limits of the generative AIs. In our Natural Language Division of the contest, we had eight Japanese speaking agent teams, and five English speaking agents, to mutually run games. By using the game logs, we performed human subjective evaluations, win rates, and detailed log analysis. We found that the entire system performance has largely improved over the previous year, due to the recent advantages of the LLMs. There are several new ideas to improve the way using LLMs such as the summarization, characterization, and the logics outside LLMs, etc. However, it is not perfect at all yet; the generated talks are sometimes inconsistent with the game actions. Our future work includes to reveal the capability of the LLMs, whether they can make the duality of the “liar”, in other words, holding a “true” and a “false” circumstances of the agent at the same time, even holding what these circumstances look like from other agents.

2001

pdf bib
A Deterministic Method for Structural Analysis of Compound Words in Japanese
Dongli Han | Takeshi Ito | Teiji Furugori
Proceedings of the 16th Pacific Asia Conference on Language, Information and Computation