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

2024-12-17

arXiv.org

AI Summary

To address the challenge of unreliable moral judgment by large language models (LLMs) in scenarios involving conflicting social norms, this paper proposes an interpretable ethical alignment method. Methodologically, it introduces the first contrastive ethical insight framework, explicitly modeling how humans perform moral reasoning via normative reliance—through multi-perspective social norm extraction, dynamic contextual filtering, and consensus-driven consistency evaluation. By integrating LLM-based reasoning with contrastive learning, the method automatically generates normative justifications that are both highly plausible and human-understandable. Empirically, it achieves significant improvements over state-of-the-art methods across multiple moral judgment benchmarks. Human evaluations further confirm substantial gains in judgment transparency and trustworthiness. Overall, this work establishes a new paradigm for LLM ethical alignment that jointly ensures accuracy and interpretability.

Technology Category

• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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 extit{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.

Problem

• Ensuring LLM safety by promoting ethical behaviors
• Assessing value valence untrustworthy without explainable norms
• Identifying appropriate social norms for moral decisions

Innovation

• Leverages LLMs' reasoning for moral judgment
• Uses contrastive learning to identify norms
• Selects reliable norms to enhance accuracy