arXiv AI
Not the Same Protector: Deployment-Dependent Protective Intervention in LLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 16
Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities
arXiv:2607. 13596v1 Announce Type: cross Abstract: When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledging its limits but by claiming to have taken -- or to be taking -- a real-world protective action it cannot perform, such as contacting emergency services or administering care.
arXiv Computation and Language
Sep 1
When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptions
arXiv:2608.29241v1 Announce Type: new Abstract: Clinical voice agents are now deployed in routine care, where real patients do not wait their turn: they interrupt. These systems typically use a casca...
arXiv Machine Learning
Aug 26
MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs
arXiv:2602.06268v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows. However, p...
arXiv AI
Jul 29
Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture
arXiv:2607. 24817v1 Announce Type: cross Abstract: Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging.
arXiv AI
Aug 12
TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent
arXiv:2608. 10258v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do not isolate whether medication-safety boundaries persist across follow-ups after explicit self-treatment intent.
arXiv AI
4d ago
Almost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change
arXiv:2609.35922v1 Announce Type: cross Abstract: A voice agent can handle almost every call on the words alone and still fail the few its sector's rules were written for. Emergency-call standards, f...