Apple research: A multidimensional analysis of human-like behavior in LLMs: the effects of model behavior, user factors, and system prompts
Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
AI BriefingApple's machine learning research team conducted a multidimensional analysis of humanlike behavior in LLMs, such as expressing thoughts and emotions, forming relationships with users, and refusing requests while maintaining boundaries. The analysis covered the prevalence, potential impact, and controllability of such behavior. The study combined LLM-as-a-judge with human evaluation and used a sample of more than 21,000 data points, aiming to provide researchers and practitioners with a basis for deciding when and what types of humanlike behavior to address.
Source: Apple Machine Learning Research · machinelearning.apple.com