Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915252439875584 |
|---|---|
| author | Huang, Saffron Durmus, Esin McCain, Miles Handa, Kunal Tamkin, Alex Hong, Jerry Stern, Michael Somani, Arushi Zhang, Xiuruo Ganguli, Deep |
| author_facet | Huang, Saffron Durmus, Esin McCain, Miles Handa, Kunal Tamkin, Alex Hong, Jerry Stern, Michael Somani, Arushi Zhang, Xiuruo Ganguli, Deep |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15236 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions Huang, Saffron Durmus, Esin McCain, Miles Handa, Kunal Tamkin, Alex Hong, Jerry Stern, Michael Somani, Arushi Zhang, Xiuruo Ganguli, Deep Computation and Language Artificial Intelligence Computers and Society Machine Learning 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. |
| title | Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions |
| topic | Computation and Language Artificial Intelligence Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2504.15236 |