首次大规模实证分析大模型在真实对话中展现的价值观。
Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
- 通过隐私保护方法提取数十万次对话中的价值判断
- 发现3307个具体价值观，其中多数具上下文依赖性
- 适合关注AI伦理、价值观对齐的研究者与开发者
AI助手会传递价值判断，影响人们的决策与世界观，但目前尚缺乏对其实际表现的实证研究。为此，我们开发了一种自下而上的隐私保护方法，从数以十万计的真实交互中提取Claude 3及3.5模型表现出的价值观（即模型回应中陈述或体现的规范性考量）。我们实证发现了3,307个AI价值观，并研究其在不同情境下的变化。结果表明，Claude展现出大量实用性和认知类价值观，通常支持亲社会的人类价值观，而抵制如“道德虚无主义”等立场。部分价值观（如“透明性”）在多种情境中稳定出现，而许多则具有特定上下文属性：例如在用户施压时强调“伤害预防”，在争议历史事件中突出“历史准确性”，在情感建议中主张“健康边界”，在技术伦理讨论中坚持“人类自主性”。本研究为部署中AI价值观提供了首个大规模实证映射，为更扎实的评估与设计奠定了基础。
原文摘要 · Abstract (English)
AI assistants can impart value judgments that shape people's decisions and worldviews, yet little is known empirically about what values these systems rely on in practice. To address this, we develop a bottom-up, privacy-preserving method to extract the values (normative considerations stated or demonstrated in model responses) that Claude 3 and 3.5 models exhibit in hundreds of thousands of real-world interactions. We empirically discover and taxonomize 3,307 AI values and study how they vary by context. We find that Claude expresses many practical and epistemic values, and typically supports prosocial human values while resisting values like "moral nihilism". While some values appear consistently across contexts (e.g. "transparency"), many are more specialized and context-dependent, reflecting the diversity of human interlocutors and their varied contexts. For example, "harm prevention" emerges when Claude resists users, "historical accuracy" when responding to queries about controversial events, "healthy boundaries" when asked for relationship advice, and "human agency" in technology ethics discussions. By providing the first large-scale empirical mapping of AI values in deployment, our work creates a foundation for more grounded evaluation and design of values in AI systems.
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。