Imagen de Portada

Measuring the Machine: Evaluating Generative AI as Pluralist Sociotechical Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Johnson, Rebecca L.
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI
por: Karagoz, Atahan
Publicado: (2026)

Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research
por: Oldenburg, Ninell, et al.
Publicado: (2025)

Pluralistic Off-policy Evaluation and Alignment
por: Huang, Chengkai, et al.
Publicado: (2025)

Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI
por: Janowicz, Krzysztof, et al.
Publicado: (2025)

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
por: Sorensen, Taylor, et al.
Publicado: (2023)

Evaluating Moral Beliefs across LLMs through a Pluralistic Framework
por: Liu, Xuelin, et al.
Publicado: (2024)

A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs
por: Srewa, Mahmoud, et al.
Publicado: (2025)

Pairwise Calibrated Rewards for Pluralistic Alignment
por: Halpern, Daniel, et al.
Publicado: (2025)

Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI
por: Alamdari, Parand A., et al.
Publicado: (2024)

Rules, Cases, and Reasoning: Positivist Legal Theory as a Framework for Pluralistic AI Alignment
por: Caputo, Nicholas A.
Publicado: (2024)

Pluralistic Alignment Over Time
por: Klassen, Toryn Q., et al.
Publicado: (2024)

A Roadmap to Pluralistic Alignment
por: Sorensen, Taylor, et al.
Publicado: (2024)

Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI
por: Harland, Hadassah, et al.
Publicado: (2024)

AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games
por: Ying, Lance, et al.
Publicado: (2026)

EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling
por: Zhang, Yujie, et al.
Publicado: (2026)

Branching Out: Broadening AI Measurement and Evaluation with Measurement Trees
por: Greenberg, Craig, et al.
Publicado: (2025)

Favi-Score: A Measure for Favoritism in Automated Preference Ratings for Generative AI Evaluation
por: von Däniken, Pius, et al.
Publicado: (2024)

Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment
por: Vamplew, Peter, et al.
Publicado: (2024)

Toward an Evaluation Science for Generative AI Systems
por: Weidinger, Laura, et al.
Publicado: (2025)

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
por: Falahati, Ali, et al.
Publicado: (2026)

Evaluating the Social Impact of Generative AI Systems in Systems and Society
por: Solaiman, Irene, et al.
Publicado: (2023)

Open-World Evaluations for Measuring Frontier AI Capabilities
por: Kapoor, Sayash, et al.
Publicado: (2026)

DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping
por: Zhu, Pengyun, et al.
Publicado: (2026)

APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs
por: Srewa, Mahmoud, et al.
Publicado: (2026)

Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression
por: Adams, Jadie, et al.
Publicado: (2025)

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
por: Guo, Hanze, et al.
Publicado: (2025)

MixDPO: Modeling Preference Strength for Pluralistic Alignment
por: Imai, Saki, et al.
Publicado: (2026)

Pluralistic Alignment for Healthcare: A Role-Driven Framework
por: Zhong, Jiayou, et al.
Publicado: (2025)

From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement
por: Vishwarupe, Varad, et al.
Publicado: (2026)

VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
por: Kim, Woojin, et al.
Publicado: (2026)

In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI
por: Longpre, Shayne, et al.
Publicado: (2025)

Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
por: LaCroix, Travis
Publicado: (2026)

VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
por: Zheng, Shenyan, et al.
Publicado: (2026)

VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare
por: Shetty, Anudeex, et al.
Publicado: (2025)

IslamicLegalBench: Evaluating LLMs Knowledge and Reasoning of Islamic Law Across 1,200 Years of Islamic Pluralist Legal Traditions
por: Elmahjub, Ezieddin, et al.
Publicado: (2026)

Dialogue with the Machine and Dialogue with the Art World: Evaluating Generative AI for Culturally-Situated Creativity
por: Qadri, Rida, et al.
Publicado: (2024)

Operationalizing Pluralistic Values in Large Language Model Alignment Reveals Trade-offs in Safety, Inclusivity, and Model Behavior
por: Ali, Dalia, et al.
Publicado: (2025)

Variance-Bounded Evaluation of Entity-Centric AI Systems Without Ground Truth: Theory and Measurement
por: Ding, Kaihua
Publicado: (2025)

Slurry-as-a-Service: A Modest Proposal on Scalable Pluralistic Alignment for Nutrient Optimization
por: Hong, Rachel, et al.
Publicado: (2026)

KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems
por: Kulibaba, Stepan, et al.
Publicado: (2025)