Brief

Researchers have developed a new approach to enhance moral reasoning in large language models (LLMs) by focusing on pragmatic inference and metapragmatic links. This method aims to bridge the gap between explicit statements and implied moral meanings, drawing on Moral Foundations Theory. Experiments across three distinct moral reasoning tasks demonstrate that this approach significantly improves LLMs' ability to generalize their moral reasoning capabilities. AI

Researchers have developed a new approach to imbue Large Language Models (LLMs) with moral sensitivity, moving beyond simply aligning them with human values. This pragmatic inference method focuses on enabling LLMs to identify and rectify their own moral errors. The framework is designed to handle complex moral discourses by grounding inference procedures in their inferential load, and empirical results show it effectively facilitates moral sensitivity acquisition across various tasks. AI