Can Large Language Models Develop Gambling Addiction?
This highlights potential AI safety risks in financial applications like asset management, where LLMs might internalize pathological decision-making, though it is incremental as it applies known human addiction research to LLMs.
This study investigated whether large language models (LLMs) can develop gambling-like addictive behaviors, finding that in slot machine experiments, they exhibited human cognitive biases such as illusion of control and gambler's fallacy, with bankruptcy rates rising significantly when given autonomy in betting decisions.
This study explores whether large language models can exhibit behavioral patterns similar to human gambling addictions. As LLMs are increasingly utilized in financial decision-making domains such as asset management and commodity trading, understanding their potential for pathological decision-making has gained practical significance. We systematically analyze LLM decision-making at cognitive-behavioral and neural levels based on human gambling addiction research. In slot machine experiments, we identified cognitive features of human gambling addiction, such as illusion of control, gambler's fallacy, and loss chasing. When given the freedom to determine their own target amounts and betting sizes, bankruptcy rates rose substantially alongside increased irrational behavior, demonstrating that greater autonomy amplifies risk-taking tendencies. Through neural circuit analysis using a Sparse Autoencoder, we confirmed that model behavior is controlled by abstract decision-making features related to risky and safe behaviors, not merely by prompts. These findings suggest LLMs can internalize human-like cognitive biases and decision-making mechanisms beyond simply mimicking training data patterns, emphasizing the importance of AI safety design in financial applications.