We attempt to improve the reasoning capability of LLMs in werewolf game by combining BDI logic with LLMs. While LLMs such as ChatGPT has been developed and used for various tasks, there remain several weakness of the LLMs. Logical reasoning is one of such weakness. Therefore, we try to introduce BDI logic-based prompts to verify the logical reasoning ability of LLMs in dialogue of werewofl game. Experiments and evaluations were conducted using “AI-Werewolf,” a communication game for AI with incomplete information. From the results of the game played by five agents, we compare the logical reasoning ability of LLMs by using the win rate and the vote rate against werewolf.

Recently, Large Language Models (LLMs) have attracted significant attention for their exceptional performance across a broad range of tasks, particularly in text analysis. However, the finance sector presents a distinct challenge due to its dependence on time-series data for complex forecasting tasks. In this study, we introduce a novel framework called LLMFactor, which employs Sequential Knowledge-Guided Prompting (SKGP) to identify factors that influence stock movements using LLMs. Unlike previous methods that relied on keyphrases or sentiment analysis, this approach focuses on extracting factors more directly related to stock market dynamics, providing clear explanations for complex temporal changes. Our framework directs the LLMs to create background knowledge through a fill-in-the-blank strategy and then discerns potential factors affecting stock prices from related news. Guided by background knowledge and identified factors, we leverage historical stock prices in textual format to predict stock movement. An extensive evaluation of the LLMFactor framework across four benchmark datasets from both the U.S. and Chinese stock markets demonstrates its superiority over existing state-of-the-art methods and its effectiveness in financial time-series forecasting.

This paper describes a Japanese political corpus created for interdisciplinary political research. The corpus contains the local assembly minutes of 47 prefectures from April 2011 to March 2015. This four-year period coincides with the term of office for assembly members in most autonomies. We analyze statistical data, such as the number of speakers, characters, and words, to clarify the characteristics of local assembly minutes. In addition, we identify problems associated with the different web services used by the autonomies to make the minutes available to the public.