2025/08/19 by Maciej Skórski, Skorski, Maciej, Alina Landowska +1
Social Sciences · #62F15 #62P25 #68T50 #Computation and Language (cs.CL) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #I.2.7 #J.4 #K.4.1 #Legal Education and Practice Innovations
paper · pdf · doi:10.48550/arxiv.2508.13804
openalex publication_date 2025/08/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/03
How do Large Language Models understand moral dimensions compared to humans? This first large-scale Bayesian evaluation of market-leading language models provides the answer. In contrast to prior work using deterministic ground truth (majority or inclusion rules), we model annotator disagreements to capture both aleatoric uncertainty (inherent human disagreement) and epistemic uncertainty (model domain sensitivity). We evaluated the best language models (Claude Sonnet 4, DeepSeek-V3, Llama 4 Maverick) across 250K+ annotations from nearly 700 annotators in 100K+ texts spanning social networks, news and forums. Our GPU-optimized Bayesian framework processed 1M+ model queries, revealing that AI models typically rank among the top 25% of human annotators, performing much better than average balanced accuracy. Importantly, we find that AI produces far fewer false negatives than humans, highlighting their more sensitive moral detection capabilities.