Imagen de Portada

Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Grey, Markov, Segerie, Charbel-Raphaël
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

The AI Risk Spectrum: From Dangerous Capabilities to Existential Threats
por: Grey, Markov, et al.
Publicado: (2025)

BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards
por: Dorn, Diego, et al.
Publicado: (2024)

The bitter lesson of misuse detection
por: Mariaccia, Hadrien, et al.
Publicado: (2025)

Unpacking Human-AI Interaction in Safety-Critical Industries: A Systematic Literature Review
por: Bach, Tita A., et al.
Publicado: (2023)

Continuous Time Continuous Space Homeostatic Reinforcement Learning (CTCS-HRRL) : Towards Biological Self-Autonomous Agent
por: Laurencon, Hugo, et al.
Publicado: (2024)

SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety
por: Röttger, Paul, et al.
Publicado: (2024)

Mechanistic Interpretability for AI Safety -- A Review
por: Bereska, Leonard, et al.
Publicado: (2024)

Responsible AI in Construction Safety: Systematic Evaluation of Large Language Models and Prompt Engineering
por: Sammour, Farouq, et al.
Publicado: (2024)

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
por: Vijayvargiya, Sanidhya, et al.
Publicado: (2025)

International Agreements on AI Safety: Review and Recommendations for a Conditional AI Safety Treaty
por: Scholefield, Rebecca, et al.
Publicado: (2025)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
por: Siu, Vincent, et al.
Publicado: (2025)

SAGE-Eval: Evaluating LLMs for Systematic Generalizations of Safety Facts
por: Yueh-Han, Chen, et al.
Publicado: (2025)

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
por: Xie, Tinghao, et al.
Publicado: (2024)

Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift
por: Vaccaro, Michelle, et al.
Publicado: (2026)

AI Safety is Stuck in Technical Terms -- A System Safety Response to the International AI Safety Report
por: Dobbe, Roel
Publicado: (2025)

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
por: Ren, Richard, et al.
Publicado: (2024)

SafePro: Evaluating the Safety of Professional-Level AI Agents
por: Zhou, Kaiwen, et al.
Publicado: (2026)

Auto-Evaluation: A Critical Measure in Driving Improvements in Quality and Safety of AI-Generated Lesson Resources
por: Clark, Hannah-Beth, et al.
Publicado: (2025)

Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems
por: Fan, Yihe, et al.
Publicado: (2025)

Generative AI for Requirements Engineering: A Systematic Literature Review
por: Cheng, Haowei, et al.
Publicado: (2024)

AI Safety: A Climb To Armageddon?
por: Cappelen, Herman, et al.
Publicado: (2024)

Safety Cases: A Scalable Approach to Frontier AI Safety
por: Hilton, Benjamin, et al.
Publicado: (2025)

The Ghost in the Grammar: Methodological Anthropomorphism in AI Safety Evaluations
por: Costa, Mariana Lins
Publicado: (2026)

Holistic Safety and Responsibility Evaluations of Advanced AI Models
por: Weidinger, Laura, et al.
Publicado: (2024)

A Different Approach to AI Safety: Proceedings from the Columbia Convening on Openness in Artificial Intelligence and AI Safety
por: François, Camille, et al.
Publicado: (2025)

NeuroAI for AI Safety
por: Mineault, Patrick, et al.
Publicado: (2024)

Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols
por: Griffin, Charlie, et al.
Publicado: (2024)

A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care
por: Normand, Oliver, et al.
Publicado: (2025)

Systematic Literature Review: Explainable AI Definitions and Challenges in Education
por: Altukhi, Zaid M., et al.
Publicado: (2025)

MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
por: Han, Tessa, et al.
Publicado: (2024)

AI Adoption in NGOs: A Systematic Literature Review
por: Rotter, Janne, et al.
Publicado: (2025)

AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement
por: Zhang, Zhexin, et al.
Publicado: (2025)

Safety Cases: How to Justify the Safety of Advanced AI Systems
por: Clymer, Joshua, et al.
Publicado: (2024)

Improving the Safety and Trustworthiness of Medical AI via Multi-Agent Evaluation Loops
por: Ghafoor, Zainab, et al.
Publicado: (2026)

Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety
por: Gringras, David
Publicado: (2026)

Data-Driven Methods and AI in Engineering Design: A Systematic Literature Review Focusing on Challenges and Opportunities
por: Afifi, Nehal, et al.
Publicado: (2025)

Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis
por: Holzner, Niklas, et al.
Publicado: (2025)

AI2-Active Safety: AI-enabled Interaction-aware Active Safety Analysis with Vehicle Dynamics
por: Wu, Keshu, et al.
Publicado: (2025)

AI in Computational Thinking Education in Higher Education: A Systematic Literature Review
por: Rahimi, Ebrahim, et al.
Publicado: (2025)

Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs
por: Li, Wenkai, et al.
Publicado: (2026)