Abstract
Current approaches to aligning large language models (LLMs) with human values often treat ethical decisions as binary classifications. We argue that this approach fails to capture the nuanced nature of real-world ethical dilemmas. We introduce an ethical ambiguity fine-tuning framework that teaches LLMs to recognize, articulate, and reason about situations where multiple valid ethical perspectives exist. Our method leverages a curated dataset of morally ambiguous scenarios annotated with diverse stakeholder perspectives. Experiments show that models fine-tuned with our approach demonstrate improved nuance in ethical reasoning while maintaining safety guardrails.