Image de couverture de livre

Questionnaire Responses Do not Capture the Safety of AI Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hellrigel-Holderbaum, Max, Young, Edward James
Format:	Preprint
Publié:	2026
Sujets:	Computers and Society Artificial Intelligence Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Against racing to AGI: Cooperation, deterrence, and catastrophic risks
par: Dung, Leonard, et autres
Publié: (2025)

Misalignment or misuse? The AGI alignment tradeoff
par: Hellrigel-Holderbaum, Max, et autres
Publié: (2025)

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
par: Ren, Richard, et autres
Publié: (2024)

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
par: Qiu, Jiahao, et autres
Publié: (2025)

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures
par: Gringras, David
Publié: (2026)

Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
par: Dong, Zhichen, et autres
Publié: (2024)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models
par: Anwar, Usman, et autres
Publié: (2024)

Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
par: Shayegani, Erfan, et autres
Publié: (2025)

When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment
par: Xiao, Yuxin, et autres
Publié: (2025)

Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropy
par: Penny-Dimri, Jahan C., et autres
Publié: (2025)

Why Do Safety Guardrails Degrade Across Languages?
par: Zhang, Max, et autres
Publié: (2026)

AI-AI Bias: large language models favor communications generated by large language models
par: Laurito, Walter, et autres
Publié: (2024)

Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI
par: Li, Zihao, et autres
Publié: (2025)

Language Agents as Digital Representatives in Collective Decision-Making
par: Jarrett, Daniel, et autres
Publié: (2025)

Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
par: Mathur, Saahil, et autres
Publié: (2026)

Do Large Language Models Walk Their Talk? Measuring the Gap Between Implicit Associations, Self-Report, and Behavioral Altruism
par: Andric, Sandro
Publié: (2025)

BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
par: Xu, Xin, et autres
Publié: (2025)

How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare
par: Schroeder, Daniel Thilo, et autres
Publié: (2025)

A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
par: Arghal, Raghu, et autres
Publié: (2026)

Prompt-Counterfactual Explanations for Generative AI System Behavior
par: Goethals, Sofie, et autres
Publié: (2026)

Understanding and Mitigating Risks of Generative AI in Financial Services
par: Gehrmann, Sebastian, et autres
Publié: (2025)

Managing extreme AI risks amid rapid progress
par: Bengio, Yoshua, et autres
Publié: (2023)

Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy
par: Tang, Xiangru, et autres
Publié: (2024)

Know Thyself? On the Incapability and Implications of AI Self-Recognition
par: Bai, Xiaoyan, et autres
Publié: (2025)

How Prevalent is Gender Bias in ChatGPT? -- Exploring German and English ChatGPT Responses
par: Urchs, Stefanie, et autres
Publié: (2023)

Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
par: Olteanu, Alexandra, et autres
Publié: (2025)

AI Sandbagging: Language Models can Strategically Underperform on Evaluations
par: van der Weij, Teun, et autres
Publié: (2024)

Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance
par: Imperial, Joseph Marvin, et autres
Publié: (2025)

The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
par: Ren, Richard, et autres
Publié: (2025)

Impacts of Racial Bias in Historical Training Data for News AI
par: Bhargava, Rahul, et autres
Publié: (2025)

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
par: Wang, Jiawei, et autres
Publié: (2024)

AI-University: An LLM-based platform for instructional alignment to scientific classrooms
par: Shojaei, Mostafa Faghih, et autres
Publié: (2025)

AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy
par: Schoenegger, Philipp, et autres
Publié: (2024)

Towards AI-$45^{\circ}$ Law: A Roadmap to Trustworthy AGI
par: Yang, Chao, et autres
Publié: (2024)

Frontier AI systems have surpassed the self-replicating red line
par: Pan, Xudong, et autres
Publié: (2024)

The Compliance Gap: Why AI Systems Promise to Follow Process Instructions but Don't
par: Shin, Kwan Soo
Publié: (2026)

Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
par: Zhang, Yue, et autres
Publié: (2023)

Whose Preferences? Differences in Fairness Preferences and Their Impact on the Fairness of AI Utilizing Human Feedback
par: Lerner, Emilia Agis, et autres
Publié: (2024)

Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models
par: Era, Jalisha Jashim, et autres
Publié: (2025)

Future of Work with AI Agents: Auditing Automation and Augmentation Potential across the U.S. Workforce
par: Shao, Yijia, et autres
Publié: (2025)