Recent advancements in large language models (LLMs) have unlocked the potential for generating high-quality game commentary. However, producing insightful and engaging commentary for complex games with incomplete information remains a significant challenge. In this paper, we introduce a novel commentary method that combines reinforcement learning (RL) and LLMs, tailored specifically for the Chinese card game Guandan. Our system leverages RL to generate intricate card-playing scenarios and employs LLMs to generate corresponding commentary text, effectively emulating the strategic analysis and narrative prowess of professional commentators. The framework comprises a state commentary guide, a Theory of Mind (ToM)-based strategy analyzer, and a style retrieval module, which seamlessly collaborate to deliver detailed and context-relevant game commentary in the Chinese language environment. We empower LLMs with ToM capabilities and refine both retrieval and information filtering mechanisms. This facilitates the generation of personalized commentary content. Our experimental results demonstrate a significant improvement in the system’s effectiveness in generating accurate, coherent, and engaging commentary when applied to open-source LLMs, surpassing GPT-4 across multiple evaluation metrics.
Su et al. (Fri,) studied this question.