CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overestimates reliability.
Human-centric evaluation for foundation models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
All five tested LLMs deviated from US race-stratified disease distributions in synthetic case generation, while retrieval-based agentic workflows improved mean p-value by 0.0348, median p-value by 0.1166, and mean difference by 0.0949 for DeepSeek V3 in diagnosis ranking.
citing papers explorer
-
CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning
CLExEval introduces a human-annotated evaluation framework on 40 rare cases that identifies verbosity bias, hidden knowledge paradox, and 68.6% reasoning-to-output mismatch in LLMs while showing LLM-as-a-Judge overestimates reliability.
-
First, Do No Harm (With LLMs): Mitigating Racial Bias via Agentic Workflows
All five tested LLMs deviated from US race-stratified disease distributions in synthetic case generation, while retrieval-based agentic workflows improved mean p-value by 0.0348, median p-value by 0.1166, and mean difference by 0.0949 for DeepSeek V3 in diagnosis ranking.