This study explores the effects of interacting with AI vs. human interlocutors on English language learners’ speaking performance in a game-based learning context. We developed Taboo Talks, a word-guessing game in which learners alternated between giving and guessing clues with either an AI or a human partner. To evaluate the impact of interaction mode on oral proficiency, participants completed a story retelling task, assessed using complexity, accuracy, and fluency (CAF) metrics. Each participant engaged in both partner conditions, with group order counterbalanced. The results from the retelling task indicated modest improvements in fluency and complexity, particularly following interaction with the AI partner. Accuracy scores remained largely stable across conditions. Post-task reflections revealed that learners perceived AI partners as less intimidating, facilitating more relaxed language production, though concerns were noted regarding limited responsiveness. Qualitative analysis of the gameplay transcripts further revealed contrasting interactional patterns: AI partners elicited more structured interactions whereas human partners prompted more spontaneous and variable interactions. These findings suggest that AI-mediated gameplay can enhance specific dimensions of spoken language development and may serve as a complementary resource alongside human interaction.

Humor translation remains a significant challenge due to its reliance on wordplay, cultural context, and nuance. This study compares a Neural Machine Translation (NMT) system (hereafter referred to as MT) with a Large Language Model (GPT-based translation using three different prompts) for translating jokes from English to Thai. Results show that GPT-based models significantly outperform MT in humor retention, with the explanation-enhanced prompt (GPT-Ex) achieving the highest joke preservation rate (62.94%) compared to 50.12% in MT. Additionally, humor loss was more frequent in MT, while GPT-based models, particularly GPT-Ex, better retained jokes. A McNemar test confirmed significant differences in annotation distributions across models. Beyond evaluation, we propose using GPT-based models with optimized prompt engineering to enhance humor translation. Our refined prompts improved joke retention by guiding the model’s understanding of humor and cultural nuances.