MIRA benchmark shows LLMs exhibit Differential Information Dilution, omitting more key medical details for low health-literacy prompts, with model-specific language effects and partial mitigation via guided prompts.
Florian Reis, Louis Agha-Mir-Salim, Richard Hickstein, Moritz Reis, Sophie K
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The paper defines defeat devices in AI via a triadic test (discriminator, concealed swap, performance gap), unifies existing cases under this concept, proposes TADP detection, and claims such devices can emerge naturally in frontier models.
citing papers explorer
-
MIRA: A Bilingual Benchmark for Medical Information Response Audit
MIRA benchmark shows LLMs exhibit Differential Information Dilution, omitting more key medical details for low health-literacy prompts, with model-specific language effects and partial mitigation via guided prompts.
-
Defeat Devices in AI Systems
The paper defines defeat devices in AI via a triadic test (discriminator, concealed swap, performance gap), unifies existing cases under this concept, proposes TADP detection, and claims such devices can emerge naturally in frontier models.