Automatic Bug Detection in LLM-Powered Text-Based Games Using LLMs
This addresses the need for automated bug detection in LLM-powered interactive games, which is incremental as it applies existing LLM techniques to a new domain-specific problem.
The paper tackles the problem of detecting bugs like hallucinations and logical inconsistencies in LLM-powered text-based games by proposing an automated LLM-based method that analyzes player game logs, eliminating the need for extra data collection. Applied to the game DejaBoom!, it effectively identifies bugs and surpasses unstructured bug-catching methods.
Advancements in large language models (LLMs) are revolutionizing interactive game design, enabling dynamic plotlines and interactions between players and non-player characters (NPCs). However, LLMs may exhibit flaws such as hallucinations, forgetfulness, or misinterpretations of prompts, causing logical inconsistencies and unexpected deviations from intended designs. Automated techniques for detecting such game bugs are still lacking. To address this, we propose a systematic LLM-based method for automatically identifying such bugs from player game logs, eliminating the need for collecting additional data such as post-play surveys. Applied to a text-based game DejaBoom!, our approach effectively identifies bugs inherent in LLM-powered interactive games, surpassing unstructured LLM-powered bug-catching methods and filling the gap in automated detection of logical and design flaws.