Fragile Preferences: A Deep Dive Into Order Effects in Large Language Models

Large language models (LLMs) are increasingly used in decision-support systems across high-stakes domains such as hiring and university admissions, where decisions often involve selecting among competing alternatives. While prior work has noted positional order biases in LLM-driven comparisons, these biases have not been systematically dissected or linked to underlying preference structures. We provide the first comprehensive investigation of positional biases across multiple LLM architectures and domains, uncovering strong and consistent order effects, including a novel centrality bias not previously documented in human or machine decision-making. We also find a quality-dependent shift: when options are high quality, models exhibit primacy bias, but favor latter options when option quality is low. We further identify a previously undocumented bias favoring certain names over others. To distinguish superficial tie-breaking from true distortions of judgment, we introduce a framework that classifies pairwise preferences as robust, fragile, or indifferent. We show that order effects can lead models to select strictly inferior options, and that positional biases are typically stronger than gender biases. These findings suggest that LLMs are not merely inheriting human-like biases, but exhibit distinct failure modes not seen in human decision-making. We propose targeted mitigation strategies, including a novel use of the temperature parameter, to reduce order-driven distortions.