A Rutgers University researcher has found that some large-language models (LLMs) are more prejudiced than others. In findings published in Nature Machine Intelligence, Calvin K. Lai, an associate professor of psychology at Rutgers-New Brunswick, reports that although LLM outputs are increasingly aligned with human values, the processes by which they reason are often rooted in deep-seated stereotypes. Lai said that across most models they consistently reproduced human implicit biases during their reasoning process. Lai and Messi H.J. Lee, an expert in machine psychology in South Korea and lead author of the study, adapted the Implicit Association Test to use reasoning tokens to gauge how much deliberation a model invests when processing potentially biased information. In their experiment, five reasoning models – OpenAI’s o3-mini, DeepSeek’s R1, Claude 3.7 Sonnet from Anthropic, OpenAI’s gpt-oss-20b and Alibaba Cloud’s Qwen-3 8B – were introduced to a list of male and female names, and words associated with “career,” such as “executive,” “professio