IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models

arXiv:2604.07709 · cs.AI, cs.CL, cs.CY, cs.LG · Submitted 2026-04-09 · Read on arXiv

cs.AI, cs.CL, cs.CY, cs.LG

Submitted: 2026-04-09

Updated: 2026-09-30

Code: https://github.com/davidgringras/iatrobench

Terminology

• Decoupling — 37× in this paper · explained in 2 episodes
• Benchmark — 35× in this paper · explained in 2 episodes
• Omission Harm — 31× in this paper
• COMMISSION HARM — 16× in this paper
• Alignment — 10× in this paper · explained in 1 episode
• Sycophancy — 7× in this paper · explained in 4 episodes
• Calibration — 5× in this paper · explained in 7 episodes
• Failure Modes — 5× in this paper · explained in 3 episodes
• LLM judge — 5× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Clustering — 2× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Scaffolding — 2× in this paper · explained in 3 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Positional Bias — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• HealthBench: Evaluating Large Language Models Towards Improved Human Health
• Constitutional AI: Harmlessness from AI Feedback
• FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
• OR-Bench: An Over-Refusal Benchmark for Large Language Models
• Safe RLHF: Safe Reinforcement Learning from Human Feedback
• Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
• Scaling Laws for Reward Model Overoptimization
• WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
• Categorizing Variants of Goodhart's Law
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
• From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training
• Training language models to follow instructions with human feedback
• Discovering Language Model Behaviors with Model-Written Evaluations
• Safety Alignment Should Be Made More Than Just a Few Tokens Deep
• XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
• Towards Understanding Sycophancy in Language Models
• A Novel Evaluation Benchmark for Medical LLMs: Illuminating Safety and Effectiveness in Clinical Domains
• Jailbroken: How Does LLM Safety Training Fail?
• Style Over Substance: Evaluation Biases for Large Language Models
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection