Moral Instruction Fine Tuning for Aligning LMs with Multiple Ethical Principles
Jongchan Choi, Mingyu Kim, Sung-Ju Lee · 2024
Research on teaching human morality to AI has evolved to enhance alignment with human commonsense based on descriptive ethics. However, Language Models (LMs) based on human commonsense are limited in comprehending various moral perspectives and making moral judgments in unusual situations. To tackle these challenges, we propose Moral Instruction Fine-Tuning (MIST) to align LMs with diverse ethical principles. We demonstrate that MIST enables diverse ethical reasoning and significantly enhances zero-shot generalization in unseen moral tasks.