REVIEW 14 cited by
Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
read the original abstract
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.
Forward citations
Cited by 14 Pith papers
-
Theoretical Limits of Language Model Alignment
The maximum reward gain under KL-regularized LM alignment is a Jeffreys divergence term, estimable as covariance from base samples, with best-of-N approaching the theoretical limit.
-
"What Are You Really Trying to Do?": Co-Creating Life Goals from Everyday Computer Use
A co-creation process for inferring and refining personal strivings from computer activity logs yields more representative goals and higher user agency than baselines in a 14-person week-long study.
-
Persona Cartography: Charting Language Model Personality Traits in Weight Space
Composable LoRA adapters can amplify or suppress OCEAN traits in LLMs, combine approximately additively, preserve moderate-scale capability, and move safety-relevant behaviours.
-
User identity conditions moral wrongness ratings in non-reasoning large language models
Implicitly conveying a user's professional role in multi-turn LLM conversations shifts moral wrongness ratings across ten common-morality rules in two non-reasoning models.
-
Beyond Independent Labels: Schwartz-Geometry Decoding for Human Value Detection
A Schwartz-aware energy decoder improves theory-coherent label sets on 19 refined values at no F1 cost, while training-time geometry and LLM prompting do not match it.
-
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting
EvalCards is a composable reporting schema and monitoring tool for AI evaluations, derived from 52 papers and 10 interviews, and applied to 5,816 models and 101,843 results to surface reporting gaps.
-
Probing Persona-Dependent Preferences in Language Models
Linear probes on residual-stream activations extract a preference vector that tracks and steers pairwise task choices across personas in Gemma-3-27B and Qwen-3.5-122B, including anti-correlated evil personas.
-
Probing Persona-Dependent Preferences in Language Models
Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.
-
Positive Alignment: Artificial Intelligence for Human Flourishing
Positive Alignment introduces AI systems that support human flourishing pluralistically and proactively while remaining safe, as a necessary complement to traditional safety-focused alignment research.
-
Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
LLMs deviate from human moral preferences in kidney allocation scenarios and rarely express indecision, though low-rank fine-tuning with few examples can improve both consistency and uncertainty calibration.
-
Positive Alignment: Artificial Intelligence for Human Flourishing
Positive Alignment is defined as AI systems that support human flourishing pluralistically while staying safe and cooperative, presented as a necessary complement to existing safety-focused alignment research.
-
Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
Embodied LLM agents exhibit emergent collaborative behaviors indicating mental models of partners in a color-matching game, detected via LLM judges and supported by positive user feedback.
-
Evaluating Generative Models as Interactive Emergent Representations of Human-Like Collaborative Behavior
LLM agents in a collaborative 2D game exhibit emergent behaviors such as perspective-taking, theory of mind, and clarification, detected by LLM judges and rated positively by human participants.
-
Positive Alignment: Artificial Intelligence for Human Flourishing
Positive Alignment is introduced as a distinct AI agenda that supports human flourishing through pluralistic and context-sensitive design, complementing traditional safety-focused alignment.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.