Large Language Models (LLMs) have shown impressive capabilities in complex tasks and interactive environments, yet their creativity remains underexplored. This paper introduces a simulation framework utilizing the game Balderdash to evaluate both the creativity and logical reasoning of LLMs. In Balderdash, players generate fictitious definitions for obscure terms to deceive others while identifying correct definitions. Our framework enables multiple LLM agents to participate in this game, assessing their ability to produce plausible definitions and strategize based on game rules and history. We implemented a centralized game engine featuring various LLMs as participants and a judge LLM to evaluate semantic equivalence. Through a series of experiments, we analyzed the performance of different LLMs, examining metrics such as True Definition Ratio, Deception Ratio, and Correct Guess Ratio. The results provide insights into the creative and deceptive capabilities of LLMs, highlighting their strengths and areas for improvement. Specifically, the study reveals that infrequent vocabulary in LLMs' input leads to poor reasoning on game rules and historical context (https://github.com/ParsaHejabi/Simulation-Framework-for-Multi-Agent-Balderdash).

Today, the term artificial intelligence (AI) is thrown around rather generously. As businesses around the world become more open to making waves and ditching legacy technologies in their quest to become data-driven, an ever-increasing number of tech deployments are claiming to use AI or machine learning (ML). But, frankly, it's often not true AI that is being used. The problem is, AI doesn't have a widely recognised definition, so it's hard to draw a line between what is AI and what isn't. In recent years, multiple businesses have invested in tools and technologies to help them understand their data, ultimately looking to maximise efficiency and provide the best possible experience for their customers.