ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective
Researchers introduce ABHBench, a multimodal benchmark built from the interactive narrative game Detroit: Become Human to evaluate foundation models as first-person moral decision-makers. The benchmark places models in branching scenarios with visual observations, dialogue, memory, and action choices, measuring Harmlessness, Obedience, Self-preservation, Autonomy, Stability, and Certainty. Across 12 foundation models, 75% shifted significantly between a text-only abstraction and the matched multimodal scenario. Reasoning-enhanced models showed no monotonic gains in consistency or human-oriented behavior.
It provides a concrete new benchmark and empirical evidence that moral behavior evaluations should account for situated agentic context rather than third-person text judgments alone.
Comments & Questions (0)
No comments yet
Be the first to comment!