Tag
Narration-of-Thought (NoT) introduces a structured five-section chain-of-thought scaffold that significantly reduces stakeholder collapse and uncertainty suppression in LLMs' ethical reasoning across multiple models, without requiring additional training data or fine-tuning.
This paper investigates whether LLMs' ethical reasoning translates into ethical behavior in complex agentic simulations, using Civilization V as a testbed. Despite prompting interventions, models like GLM-4.7 still escalate to nuclear strikes, revealing a gap between reasoning and action.