A Multi-faceted Analysis of Cognitive Abilities: Evaluating Prompt Methods with Large Language Models on the CONSORT Checklist

TL;DR

This paper evaluates large language models' ability to assess clinical trial reports against CONSORT standards, revealing significant calibration issues and emphasizing the need for improved reliability in medical AI applications.

Contribution

It introduces a systematic comparison of LLMs' calibration and reasoning in medical evaluation, highlighting the importance of prompt strategies and calibration metrics.

Findings

Both models exhibit overconfidence and miscalibration.

Calibration errors remain high under clinical role-play scenarios.

Prompt engineering can influence model reliability.

Abstract

Despite the rapid expansion of Large Language Models (LLMs) in healthcare, robust and explainable evaluation of their ability to assess clinical trial reporting according to CONSORT standards remains an open challenge. In particular, uncertainty calibration and metacognitive reliability of LLM reasoning are poorly understood and underexplored in medical automation. This study applies a behavioral and metacognitive analytic approach using an expert-validated dataset, systematically comparing two representative LLMs - one general and one domain-specialized - across three prompt strategies. We analyze both cognitive adaptation and calibration error using metrics: Expected Calibration Error (ECE) and a baseline-normalized Relative Calibration Error (RCE) that enables reliable cross-model comparison. Our results reveal pronounced miscalibration and overconfidence in both models, especially under clinical role-playing conditions, with calibration error persisting above clinically relevant thresholds. These findings underscore the need for improved calibration, transparent code, and strategic prompt engineering to develop reliable and explainable medical AI.