Strategic Insights in Human and Large Language Model Tactics at Word Guessing Games
This work addresses the problem of understanding human and AI performance in word-guessing games, but it is incremental as it applies existing methods to new data without major breakthroughs.
The paper analyzed strategies of human players in a popular word-guessing game over two years, based on a survey of 25% of frequent players, and tested several large language models (LLMs) on the game in two languages, finding issues like incorrect guess lengths, repetitions, and hallucinations of non-existent words.
At the beginning of 2022, a simplistic word-guessing game took the world by storm and was further adapted to many languages beyond the original English version. In this paper, we examine the strategies of daily word-guessing game players that have evolved during a period of over two years. A survey gathered from 25% of frequent players reveals their strategies and motivations for continuing the daily journey. We also explore the capability of several popular open-access large language model systems and open-source models at comprehending and playing the game in two different languages. Results highlight the struggles of certain models to maintain correct guess length and generate repetitions, as well as hallucinations of non-existent words and inflections.