newsGoogle News — LLMTrust 62 · AggregatorPublished 7d agoLive · 6d ago
Safety and security of large language models in healthcare - Nature
Safety and security of large language models in healthcare Nature
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 64%Safety That Does Not Transfer: Cross-Lingual Clinical Correctness Drift in Deployable Medical Language Models →
- PossiblePossibly related (embedding) · 57%A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems →
- PossiblePossibly related (embedding) · 56%When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space →
- PossiblePossibly related (embedding) · 53%Evaluating Large Language Models on Misconceptions in Multi-Turn Medical Conversations →
- PossiblePossibly related (embedding) · 50%BabelSteering: Multilingual Safety Alignment via English Steering Vectors →
Covers
paperSafety That Does Not Transfer: Cross-Lingual Clinical Correctness Drift in Deployable Medical Language ModelspaperA Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open ProblemspaperWhen Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk SpacepaperEvaluating Large Language Models on Misconceptions in Multi-Turn Medical ConversationspaperBabelSteering: Multilingual Safety Alignment via English Steering Vectors
Related across the graph
paperEvaluating Large Language Models on Misconceptions in Multi-Turn Medical ConversationspaperWhen Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk SpacepaperBabelSteering: Multilingual Safety Alignment via English Steering VectorspaperA Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open ProblemspaperSafety That Does Not Transfer: Cross-Lingual Clinical Correctness Drift in Deployable Medical Language Models