Pragmatic Inference for Moral Reasoning Acquisition: Generalization via Distributional Semantics

2025-09-28

AI Summary

Large language models (LLMs) exhibit poor generalization in moral reasoning due to their reliance on distributional semantics, whereas moral judgment is inherently pragmatic and context-sensitive. To bridge this gap between distributional representation and pragmatic inference, we propose the first pragmatic inference framework grounded in Moral Foundations Theory (MFT), which explicitly models the mapping between contextual semantics and moral principles. Our method integrates context-aware pragmatic modeling, MFT-informed prompt engineering, and lightweight fine-tuning, augmented by distributional semantic analysis and dynamic contextual representation techniques. Experiments demonstrate substantial improvements in cross-domain and cross-cultural moral reasoning generalization—achieving an average +18.7% accuracy gain over baselines. The framework delivers a novel, interpretable, and transferable paradigm for moral alignment, advancing both theoretical understanding and practical deployment of ethically grounded LLMs.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Philosophy and Ethics of AI: Morality & Value-based AI
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Moral reasoning has emerged as a promising research direction for Large Language Models (LLMs), yet achieving generalization remains a central challenge. From a linguistic standpoint, this difficulty arises because LLMs are adept at capturing distributional semantics, which fundamentally differs from the morals which operate at the pragmatic level. This paper investigates how LLMs can achieve generalized moral reasoning despite their reliance on distributional semantics. We propose pragmatic inference methods grounded in moral foundations theory, which leverage contextual information at each step to bridge the pragmatic gap and guide LLMs in connecting moral foundations with moral reasoning objectives. Experimental results demonstrate that our approach significantly enhances LLMs' generalization in moral reasoning, providing a foundation for future research grounded in moral foundations theory.

Problem

• Achieving generalization in moral reasoning for LLMs
• Bridging the gap between distributional and pragmatic semantics
• Connecting moral foundations with reasoning objectives

Innovation

• Pragmatic inference methods bridge semantic-pragmatic gap
• Leverage contextual information for moral reasoning
• Guide LLMs using moral foundations theory