Copertina

Who Should Run Advanced AI Evaluations -- AISIs?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Stein, Merlin, Gandhi, Milan, Kriecherbauer, Theresa, Oueslati, Amin, Trager, Robert
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computers and Society
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Regulating AI Agents
di: Gardhouse, Kathrin, et al.
Pubblicazione: (2026)

Societal Capacity Assessment Framework: Measuring Resilience to Inform Advanced AI Risk Management
di: Gandhi, Milan, et al.
Pubblicazione: (2025)

Relational Archetypes: A Comparative Analysis of AV-Human and Agent-Human Interactions
di: Lorente, Antoni, et al.
Pubblicazione: (2026)

Watching the Watchers: A Comparative Fairness Audit of Cloud-based Content Moderation Services
di: Hartmann, David, et al.
Pubblicazione: (2024)

Monitoring Human Dependence On AI Systems With Reliance Drills
di: Hunter, Rosco, et al.
Pubblicazione: (2024)

Which Information should the UK and US AISI share with an International Network of AISIs? Opportunities, Risks, and a Tentative Proposal
di: Thurnherr, Lara
Pubblicazione: (2025)

The Role of Governments in Increasing Interconnected Post-Deployment Monitoring of AI
di: Stein, Merlin, et al.
Pubblicazione: (2024)

Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems
di: Bucknall, Ben, et al.
Pubblicazione: (2025)

How are AI agents used? Evidence from 177,000 MCP tools
di: Stein, Merlin
Pubblicazione: (2026)

Impact Matters! An Audit Method to Evaluate AI Projects and their Impact for Sustainability and Public Interest
di: Züger, Theresa, et al.
Pubblicazione: (2026)

Governing Through the Cloud: The Intermediary Role of Compute Providers in AI Regulation
di: Heim, Lennart, et al.
Pubblicazione: (2024)

How Should AI Safety Benchmarks Benchmark Safety?
di: Yu, Cheng, et al.
Pubblicazione: (2026)

AI Evaluation Should Require Standardized Item-Level Data Releases
di: Jiang, Han, et al.
Pubblicazione: (2026)

Position: AI Evaluations Should be Grounded on a Theory of Capability
di: Jo, Nathanael, et al.
Pubblicazione: (2025)

Who Would Chatbots Vote For? Political Preferences of ChatGPT and Gemini in the 2024 European Union Elections
di: Haman, Michael, et al.
Pubblicazione: (2024)

Why AI Is WEIRD and Should Not Be This Way: Towards AI For Everyone, With Everyone, By Everyone
di: Mihalcea, Rada, et al.
Pubblicazione: (2024)

Who is using AI to code? Global diffusion and impact of generative AI
di: Daniotti, Simone, et al.
Pubblicazione: (2025)

When Should AI Read the Room? Public Perceptions of Social Intelligence in AI Agents
di: Mathur, Leena, et al.
Pubblicazione: (2026)

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

Should I use Synthetic Data for That? An Analysis of the Suitability of Synthetic Data for Data Sharing and Augmentation
di: Kulynych, Bogdan, et al.
Pubblicazione: (2026)

Theory Trace Card: Theory-Driven Socio-Cognitive Evaluation of LLMs
di: Karimi-Malekabadi, Farzan, et al.
Pubblicazione: (2026)

AI Safety Frameworks Should Include Procedures for Model Access Decisions
di: Kembery, Edward, et al.
Pubblicazione: (2024)

Who's Asking? Simulating Role-Based Questions for Conversational AI Evaluation
di: Kaur, Navreet, et al.
Pubblicazione: (2025)

Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluations
di: Reuel, Anka, et al.
Pubblicazione: (2025)

When Algorithms Meet Artists: Semantic Compression of Artists' Concerns in the Public AI-Art Debate
di: Mukherjee-Gandhi, Ariya, et al.
Pubblicazione: (2025)

Who Decides in AI-Mediated Learning? The Agency Allocation Framework
di: Borchers, Conrad, et al.
Pubblicazione: (2026)

Who Gets Flagged? The Pluralistic Evaluation Gap in AI Content Watermarking
di: Nemecek, Alexander, et al.
Pubblicazione: (2026)

When Should Algorithms Resign? A Proposal for AI Governance
di: Bhatt, Umang, et al.
Pubblicazione: (2024)

AI Agents Should be Regulated Based on the Extent of Their Autonomous Operations
di: Osogami, Takayuki
Pubblicazione: (2025)

Agentic AI Systems Should Be Designed as Marginal Token Allocators
di: Zhu, Siqi
Pubblicazione: (2026)

Comprehensive AI governance requires addressing non-model gains
di: Goemans, Arthur, et al.
Pubblicazione: (2026)

(When) Should We Delegate AI Governance to AIs? Some Lessons from Administrative Law
di: Caputo, Nicholas
Pubblicazione: (2025)

Who Controls the Conversation? User Perspectives On Generative AI (LLM) System Prompts
di: Neumann, Anna, et al.
Pubblicazione: (2026)

Propensity towards Ownership and Use of Automated Vehicles: Who Are the Adopters? Who Are the Non-adopters? Who Is Hesitant?
di: Le, Tho, et al.
Pubblicazione: (2024)

AI Safety Should Prioritize the Future of Work
di: Hazra, Sanchaita, et al.
Pubblicazione: (2025)

What Should Frontier AI Developers Disclose About Internal Deployments?
di: Charnock, Jacob, et al.
Pubblicazione: (2026)

Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGI
di: Bojic, Ljubisa, et al.
Pubblicazione: (2025)

The Who in XAI: How AI Background Shapes Perceptions of AI Explanations
di: Ehsan, Upol, et al.
Pubblicazione: (2021)

Should AI Become an Intergenerational Civil Right?
di: Crowcroft, Jon, et al.
Pubblicazione: (2025)

Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization
di: Kim, HyunJin, et al.
Pubblicazione: (2025)