Benchmarking reliability and calibration of LLMs for multi-cancer early detection test communication

To assess the reliability and confidence calibration of Large Language Models (LLMs) when communicating multi-cancer early detection (MCED) test characteristics in an expert-informed clinical evaluation.

We curated 19 papers regarding prominent MCED tests and trials. Using Google's NotebookLM, we generated a question set that two MCED experts reviewed and finalized, comprising 94 multiple-choice questions (MCQs) and 13 free-response questions (FRQs). Five LLMs (ChatGPT, Claude, Gemini, Perplexity, OpenEvidence) each completed the question set three times. All models except OpenEvidence reported a confidence score (1-100) for every answer. We evaluated mean MCQ, FRQ, and overall accuracy. Confidence calibration for MCQs was assessed using reliability plots, Brier scores, and two high-confidence error metrics: proportion of answers with confidence ≥80 that were incorrect and proportion of incorrect answers with confidence ≥80. Between-model MCQ comparisons used Cochran's Q and post hoc McNemar tests; FRQ comparisons used Friedman test.

All models demonstrated high overall accuracy. Gemini achieved the highest performance (96.5% MCQ, 96% FRQ, 96.3% overall), though comparisons involving Gemini should be interpreted cautiously as it was evaluated under different time and blinding conditions. MCQ performance differed significantly across models, while FRQ performance did not. Most errors involved recalling precise numerical estimates. Despite low Brier scores across models, several models made high-confidence errors.

Subdomain and calibration analyses revealed systematic weaknesses in numerical recall and confidence reliability despite strong accuracy.

LLMs may support communication of MCED information, but clinical use should incorporate verification workflows and human oversight.