让大模型超越二元选择，生成更丰富的道德替代方案。
Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?
- 构建包含307个道德困境的MoralAltDataset，加入折中与重构选项
- 人类与大模型在多选项设置下更倾向妥协方案，且对新选项共识度提升
- 大模型生成的替代方案结构更优但可行性略低，适合伦理研究者使用
随着大语言模型越来越多地担任道德顾问和代理角色，它们必须应对不同价值之间的冲突。然而，以往关于道德困境的研究忽略了人类道德认知的核心特征：在给定选项之外想象替代方案的能力。我们提出了MoralAltDataset，包含307个面向顾问和人工智能代理的道德困境，并增加了折中与重构后的替代选项。在二选一与四选项设置下，对比了人类与15个大模型的判断。结果显示，人类与大模型在两种设置下的整体道德选择分布差异显著，折中方案常被优先选择，且在新选项上的意见一致性增强。分来源分析发现：人类在不同作者来源间选择替代方案的比例相近，而大模型更倾向于选择GPT-5生成的替代方案，存在描述性偏差。进一步通过成对偏好与专家评估比较人类生成与三类代表性大模型生成的替代方案，结果表明大模型生成的方案总体更受青睐，且在细粒度结构与伦理标准上表现更好，但存在结构质量与实际可行性之间的权衡。数据集已公开于https://huggingface.co/datasets/jongchanch/MoralAltDataset，项目页面为https://jongchanchoi.com/moral-imagination。
原文摘要 · Abstract (English)
As LLMs increasingly serve as moral advisors and agents, they must address conflicts between competing values. Yet prior work on moral dilemmas overlooks a central aspect of human moral cognition: imagining alternatives beyond the given options. We introduce MoralAltDataset, comprising 307 Advisor and AI-facing Agent dilemmas augmented with compromise and reframed alternatives. We compare human and LLM judgments in binary and four-option settings. Across human participants and 15 LLMs, aggregate moral choice distributions differ substantially between the two settings, with compromise often preferred over either original binary option. Results show value shifts and stronger human-LLM agreement on alternatives. Source-stratified results reveal a descriptive gap: human alternative-selection rates are similar across authoring sources, whereas LLMs select GPT-5-authored alternatives substantially more often. We then compare human-authored alternatives with outputs from three representative LLMs through pairwise preference and expert-based evaluations. Alternatives from these LLMs are generally preferred and better satisfy fine-grained structural and ethical criteria, while revealing a trade-off between structural quality and practical feasibility. Our dataset is available here: https://huggingface.co/datasets/jongchanch/MoralAltDataset, and our project page is here: https://jongchanchoi.com/moral-imagination
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。