Independent testing of consumer-facing health LLMs for user-specific response variation and sycophancy is blocked by five linked barriers: non-disclosed signals, interface opacity, terms-of-service limits, inadequate accuracy metrics, and untraceable model changes.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes subsampling and reweighting for scalable, consistent counterfactual risk estimation in rare-event longitudinal survival data.
citing papers explorer
-
Testing the Black Box: Structural Barriers to Independent Evaluation of Consumer-Facing Health LLMs
Independent testing of consumer-facing health LLMs for user-specific response variation and sycophancy is blocked by five linked barriers: non-disclosed signals, interface opacity, terms-of-service limits, inadequate accuracy metrics, and untraceable model changes.
-
Scalable Counterfactual Risk Estimation for Rare Events in Longitudinal Data
Proposes subsampling and reweighting for scalable, consistent counterfactual risk estimation in rare-event longitudinal survival data.