ClarityEthic: Explainable Moral Judgment Utilizing Contrastive Ethical Insights from Large Language Models

TL;DR

ClarityEthic is a novel approach that uses contrastive learning with large language models to identify relevant social norms and improve the accuracy and explainability of moral judgments.

Contribution

It introduces a new method leveraging LLM reasoning and contrastive learning to select appropriate norms for moral decision-making, enhancing interpretability and performance.

Findings

Outperforms state-of-the-art in moral judgment accuracy

Provides plausible social norm explanations for judgments

Human evaluations confirm explanation quality

Abstract

With the rise and widespread use of Large Language Models (LLMs), ensuring their safety is crucial to prevent harm to humans and promote ethical behaviors. However, directly assessing value valence (i.e., support or oppose) by leveraging large-scale data training is untrustworthy and inexplainable. We assume that emulating humans to rely on social norms to make moral decisions can help LLMs understand and predict moral judgment. However, capturing human values remains a challenge, as multiple related norms might conflict in specific contexts. Consider norms that are upheld by the majority and promote the well-being of society are more likely to be accepted and widely adopted (e.g., "don't cheat,"). Therefore, it is essential for LLM to identify the appropriate norms for a given scenario before making moral decisions. To this end, we introduce a novel moral judgment approach called \textit{ClarityEthic} that leverages LLMs' reasoning ability and contrastive learning to uncover relevant social norms for human actions from different perspectives and select the most reliable one to enhance judgment accuracy. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches in moral judgment tasks. Moreover, human evaluations confirm that the generated social norms provide plausible explanations that support the judgments. This suggests that modeling human moral judgment with the emulating humans moral strategy is promising for improving the ethical behaviors of LLMs.