Large language models can appear remarkably consistent when they recommend a meal, rank job candidates, or help users make everyday choices. Large language models can reproduce social biases present in their training data, but they may also develop system-specific tendencies that are difficult to anticipate from human psychology alone. The approach could serve as a diagnostic tool before AI systems are deployed in hiring, healthcare, education, or other environments where recommendations affect people’s lives. The researchers emphasize that their findings do not mean language models are incapable of making useful comparisons. Subject of Research: Order effects and model-specific biases in large language modelsArticle Title: Fragile preferences: A deep dive into order effects in large language modelsReferences: PNAS Nexus, article published 11-Aug-2026KeywordsLarge language models, artificial intelligence, AI bias, order effects, position bias, machine learning, resume screening, algorithmic fairness, model reliability, temperature sampling