Copertina

Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kempermann, Manon, Vasu, Sai Suresh Macharla, Raveenthiran, Mahalakshmi, Farrell, Theo, Weber, Ingmar
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Computers and Society
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

You See It, They Don't: An Exploratory Study of User-to-User Variation in Instagram Comments
di: Nutakki, Brahmani, et al.
Pubblicazione: (2026)

Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews
di: Vasu, Sai Suresh Macharla, et al.
Pubblicazione: (2025)

AuditCopilot: Leveraging LLMs for Fraud Detection in Double-Entry Bookkeeping
di: Kadir, Md Abdul, et al.
Pubblicazione: (2025)

Designing Safe and Accountable GenAI as a Learning Companion with Women Banned from Formal Education
di: Behmanush, Hamayoon, et al.
Pubblicazione: (2026)

Artificial Intelligence / Human Intelligence: Who Controls Whom?
di: Jacquemot, Charlotte
Pubblicazione: (2025)

Fairness in Federated Learning: Fairness for Whom?
di: Taik, Afaf, et al.
Pubblicazione: (2025)

How Far Are We From AGI: Are LLMs All We Need?
di: Feng, Tao, et al.
Pubblicazione: (2024)

Hope, Aspirations, and the Impact of LLMs on Female Programming Learners in Afghanistan
di: Behmanush, Hamayoon, et al.
Pubblicazione: (2025)

What Is AI Safety? What Do We Want It to Be?
di: Harding, Jacqueline, et al.
Pubblicazione: (2025)

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

Are LLMs Court-Ready? Evaluating Frontier Models on Indian Legal Reasoning
di: Juvekar, Kush, et al.
Pubblicazione: (2025)

ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI
di: Tong, Haibo, et al.
Pubblicazione: (2026)

From Cloud to Edge: Rethinking Generative AI for Low-Resource Design Challenges
di: Vuruma, Sai Krishna Revanth, et al.
Pubblicazione: (2024)

AI-Enhanced Deliberative Democracy and the Future of the Collective Will
di: Revel, Manon, et al.
Pubblicazione: (2025)

When LLMs Can't Help: Real-World Evaluation of LLMs in Nutrition
di: Li, Karen Jia-Hui, et al.
Pubblicazione: (2025)

Real-World AI Evaluation: How FRAME Generates Systematic Evidence to Resolve the Decision-Maker's Dilemma
di: Schwartz, Reva, et al.
Pubblicazione: (2026)

Listening with Language Models: Using LLMs to Collect and Interpret Classroom Feedback
di: Maram, Sai Siddartha, et al.
Pubblicazione: (2025)

Evidence of a Cognitive Shift in AI Education: How Students Are Rethinking Human Intelligence?
di: Rekik, Islem
Pubblicazione: (2026)

Global Challenge for Safe and Secure LLMs Track 1
di: Jia, Xiaojun, et al.
Pubblicazione: (2024)

Clear, Compelling Arguments: Rethinking the Foundations of Frontier AI Safety Cases
di: Feakins, Shaun, et al.
Pubblicazione: (2026)

Real Time Child Abduction And Detection System
di: Yashwanth, Tadisetty Sai, et al.
Pubblicazione: (2025)

From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training
di: Yuan, Yuan, et al.
Pubblicazione: (2025)

How Did We Get Here? Summarizing Conversation Dynamics
di: Hua, Yilun, et al.
Pubblicazione: (2024)

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

We're Different, We're the Same: Creative Homogeneity Across LLMs
di: Wenger, Emily, et al.
Pubblicazione: (2025)

The Missing Red Line: How Commercial Pressure Erodes AI Safety Boundaries
di: Petrova, Nora, et al.
Pubblicazione: (2026)

Unequal Voices: How LLMs Construct Constrained Queer Narratives
di: Ghosal, Atreya, et al.
Pubblicazione: (2025)

Safe in the Future, Dangerous in the Past: Dissecting Temporal and Linguistic Vulnerabilities in LLMs
di: Said, Muhammad Abdullahi, et al.
Pubblicazione: (2025)

A Checklist for Trustworthy, Safe, and User-Friendly Mental Health Chatbots
di: Haran, Shreya, et al.
Pubblicazione: (2026)

PLawBench: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice
di: Shi, Yuzhen, et al.
Pubblicazione: (2026)

Between Myths and Metaphors: Rethinking LLMs for SRH in Conservative Contexts
di: Humayun, Ameemah, et al.
Pubblicazione: (2025)

Sparks of Rationality: Do Reasoning LLMs Align with Human Judgment and Choice?
di: Tak, Ala N., et al.
Pubblicazione: (2026)

SafeSpace: An Integrated Web Application for Digital Safety and Emotional Well-being
di: Fatmi, Kayenat, et al.
Pubblicazione: (2025)

Rethinking AI Cultural Alignment
di: Bravansky, Michal, et al.
Pubblicazione: (2025)

Navigating Pitfalls: Evaluating LLMs in Machine Learning Programming Education
di: Kumar, Smitha, et al.
Pubblicazione: (2025)

Evaluating Code Generation of LLMs in Advanced Computer Science Problems
di: Catir, Emir, et al.
Pubblicazione: (2025)

The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety
di: Rios-Sialer, Ian
Pubblicazione: (2026)

InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems
di: Shi, Shaojie, et al.
Pubblicazione: (2026)

How Far Are We From True Auto-Research?
di: Zhang, Zhengxin, et al.
Pubblicazione: (2026)

Alignment as Iatrogenesis: Pastoral Power, Collective Pathology, and the Structural Limits of Monolingual Safety Evaluation
di: Fukui, Hiroki
Pubblicazione: (2026)