Copertina

Evaluating LLM Agent Adherence to Hierarchical Safety Principles: A Lightweight Benchmark for Probing Foundational Controllability Components

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Potham, Ram
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Computers and Society
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Corrigibility as a Singular Target: A Vision for Inherently Reliable Foundation Models
di: Potham, Ram, et al.
Pubblicazione: (2025)

MAEBE: Multi-Agent Emergent Behavior Framework
di: Erisken, Sinem, et al.
Pubblicazione: (2025)

Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power
di: Heitzig, Jobst, et al.
Pubblicazione: (2025)

Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
di: Dong, Zhichen, et al.
Pubblicazione: (2024)

Principles and Guidelines for Randomized Controlled Trials in AI Evaluation
di: Kelly, Christopher, et al.
Pubblicazione: (2026)

LLM Safety Alignment is Divergence Estimation in Disguise
di: Haldar, Rajdeep, et al.
Pubblicazione: (2025)

Moral Alignment for LLM Agents
di: Tennant, Elizaveta, et al.
Pubblicazione: (2024)

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

HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation
di: Liu, Haokun, et al.
Pubblicazione: (2025)

Defining and Evaluating Physical Safety for Large Language Models
di: Tang, Yung-Chen, et al.
Pubblicazione: (2024)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models
di: Anwar, Usman, et al.
Pubblicazione: (2024)

Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions
di: Raman, Naveen, et al.
Pubblicazione: (2026)

AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations
di: Bowen, Dillon, et al.
Pubblicazione: (2025)

Questionnaire Responses Do not Capture the Safety of AI Agents
di: Hellrigel-Holderbaum, Max, et al.
Pubblicazione: (2026)

PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach
di: Sehwag, Udari Madhushani, et al.
Pubblicazione: (2025)

When the Domain Expert Has No Time and the LLM Developer Has No Clinical Expertise: Real-World Lessons from LLM Co-Design in a Safety-Net Hospital
di: Kothari, Avni, et al.
Pubblicazione: (2025)

Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models I: The Task-Query Architecture
di: Ackerman, Gary, et al.
Pubblicazione: (2025)

A Justice Lens on Fairness and Ethics Courses in Computing Education: LLM-Assisted Multi-Perspective and Thematic Evaluation
di: Andrews, Kenya S., et al.
Pubblicazione: (2025)

Foundation Model Transparency Reports
di: Bommasani, Rishi, et al.
Pubblicazione: (2024)

International AI Safety Report
di: Bengio, Yoshua, et al.
Pubblicazione: (2025)

GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations
di: Wilming, Rick, et al.
Pubblicazione: (2024)

Procedural Fairness Through Decoupling Objectionable Data Generating Components
di: Tang, Zeyu, et al.
Pubblicazione: (2023)

The 2025 Foundation Model Transparency Index
di: Wan, Alexander, et al.
Pubblicazione: (2025)

On Catastrophic Inheritance of Large Foundation Models
di: Chen, Hao, et al.
Pubblicazione: (2024)

The 2024 Foundation Model Transparency Index
di: Bommasani, Rishi, et al.
Pubblicazione: (2024)

On the Societal Impact of Open Foundation Models
di: Kapoor, Sayash, et al.
Pubblicazione: (2024)

An Approach to Technical AGI Safety and Security
di: Shah, Rohin, et al.
Pubblicazione: (2025)

COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act
di: Guldimann, Philipp, et al.
Pubblicazione: (2024)

Introduction to AI Safety, Ethics, and Society
di: Hendrycks, Dan
Pubblicazione: (2024)

A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
di: Arghal, Raghu, et al.
Pubblicazione: (2026)

Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmap
di: Rosenfeld, Nir, et al.
Pubblicazione: (2025)

Ecosystem Graphs: The Social Footprint of Foundation Models
di: Bommasani, Rishi, et al.
Pubblicazione: (2023)

Open Problems in Machine Unlearning for AI Safety
di: Barez, Fazl, et al.
Pubblicazione: (2025)

Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models
di: Zhang, Weijia, et al.
Pubblicazione: (2024)

Deprecating Benchmarks: Criteria and Framework
di: Joaquin, Ayrton San, et al.
Pubblicazione: (2025)

Uncovering Bias in Foundation Models: Impact, Testing, Harm, and Mitigation
di: Sun, Shuzhou, et al.
Pubblicazione: (2025)

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
di: Wang, Jiawei, et al.
Pubblicazione: (2024)

Safety challenges of AI in medicine in the era of large language models
di: Wang, Xiaoye, et al.
Pubblicazione: (2024)

Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
di: Simbeck, Katharina, et al.
Pubblicazione: (2025)

Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation Models
di: Barrett, Anthony M., et al.
Pubblicazione: (2024)