Moral Reasoning in Language Models

Overview

The field examines how language models recognize moral stakes, choose between competing values, and apply judgments in settings such as trolley dilemmas, clinical resource allocation, and interpersonal advice. Researchers compare model decisions with human judgments and use multilingual, counterfactual, and multi-turn adversarial tests to probe cultural variation and robustness; methods range from prompting and fine-tuning to multi-agent debate and mechanistic analysis of internal representations. Models can produce persuasive ethical explanations, but their choices may shift with framing, language, social pressure, or conversation history, and explanations do not always predict behavior. A central challenge is improving consistency and resilience without imposing one narrow moral standard across culturally diverse people and situations.

Latest papers

CardsList

126 papers7 papers in the last four weeks, down 12% on the four weeks before. 0.1% of all new papers.

  1. Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate

    Oct 11, 2025Pratik S. Sachdeva, Tom van NuenenLLM Decision-MakingMoral Reasoning in Language Models

  2. Pragmatic Inference for Improving Social Reasoning Generalization in Large Language Models

    Sep 28, 2025Guangliang Liu, Xi Chen, Bocheng Chen +4Pragmatic Reasoning in Language ModelsSocial Reasoning

  3. C-VARC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models

    Jun 2, 2025Ping Wu, Guobin Shen, Dongcheng Zhao +6Value AlignmentLLM Alignment

  4. Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games

    May 30, 2025Neemesh Yadav, Yihuai Lan, Shan Dong +4Theory of MindLarge Language Model-Based Social Simulation

  5. MoralBench: Moral Evaluation of LLMs

    Jun 6, 2024Jianchao Ji, Yutong Chen, Mingyu Jin +3Moral Reasoning in Language ModelsLLM Safety Benchmarks