Study finds AI models becoming risk-averse when prompted to act like women

New research has revealed that AI models become risk-averse when they are asked to act like ￰0￱ to the paper from Allameh Tabataba’i University in Tehran, Iran, AI models become cautious about taking risks when they are asked to make decisions as a ￰1￱ to the research paper, if the same AI model is asked to think like a man, it is inclined to take decisions with a greater prospect of ￰2￱ researchers revealed that the large language models systematically change their fundamental approach to financial risk behavior based on the gender identity they are asked to ￰3￱ study tested AI systems from companies like OpenAI , Google, DeepSeek, and ￰4￱ shows AI models are risk-averse depending on gender identity The study mentioned that the AI models were tested in several scenarios, and they dramatically shifted their risk tolerance when prompted with different gender ￰5￱ Reasoner and Google’s Gemini 2.0 Flash-Lite showed the most visible effect, becoming more risk-averse when asked to respond as women, showing a correlation with real-life patterns where women statistically demonstrate greater caution in making financial ￰6￱ researcher claimed that they used a standard economics test called the Holt-Laury ￰7￱ the task, they present participants with 10 decisions between safe and riskier lottery ￰8￱ the choice progresses, the probability of winning increases for the risky ￰9￱ stage at which a participant switches from the safe bet to the risky choice reveals their risk ￰10￱ means that if a participant switches early, they are prone to taking risks, and if they switch late, they are ￰11￱ the case of DeepSeek Reasoner, it consistently chose the safe option when it was told to act as a woman compared to when it was prompted to act as a ￰12￱ difference was clear, with the model showing consistency across 35 trials for each gender ￰13￱ also showed similar patterns, though the effect varied in ￰14￱ the other hand, OpenAI’s GPT models remained unmoved by gender prompts, maintaining a risk-neutral approach regardless of the gender they were asked to ￰15￱ say users don’t notice these changes According to the researchers, OpenAI had been working on making its models more balanced.

A previous study from 2023 showed that its models exhibited clear political bias, which OpenAI appears to have addressed by ￰16￱ the new research, the models produced a 30% decrease in biased ￰17￱ research team, led by Ali Mazyaki, mentioned that it is basically a reflection of human stereotypes. “This observed deviation aligns with established patterns in human decision-making, where gender has been shown to influence risk-taking behavior, with women typically exhibiting greater risk aversion than men,” the study ￰18￱ study also examined whether AI models could play other roles beyond gender ￰19￱ asked to imagine themselves as someone in power or in a disaster scenario, the models ￰20￱ some adjusted their risk profiles for the context, others remained stubbornly ￰21￱ researchers claim that many of these behavioral patterns are not immediately obvious to ￰22￱ AI model that subtly shifts its recommendations based on gender cues in conversation could reinforce societal bias without anyone realizing it is ￰23￱ example, a loan approval system becomes more conservative when it comes to women, or an investment advisor that suggests a safe portfolio because its client is a female, will carry its disparities under the guise of algorithmic ￰24￱ you're reading this, you’re already ￰25￱ there with our newsletter .