MétaCan
Menu
Back to cohort
Record W4410060872 · doi:10.1038/s41746-025-01589-z

Expert of Experts Verification and Alignment (EVAL) Framework for Large Language Models Safety in Gastroenterology

2025· article· en· W4410060872 on OpenAlexaff
Mauro Giuffrè, Kisung You, Simone Kresevic, Sunny Chung, Ryan Chen, Youngmin Ko, Colleen Chan, Theo Saarinen, Miloš Ajčević, Lory Saveria Crocè, Guadalupe García–Tsao, Ian M. Gralnek, Joseph J.�Y. Sung, Alan Barkun, Loren Laine, Jasjeet S. Sekhon, Bradly C. Stadie, Dennis Shung

Bibliographic record

Venuenpj Digital Medicine · 2025
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsMcGill University
FundersNational Institute of Diabetes and Digestive and Kidney DiseasesNational Institutes of Health
KeywordsComputer scienceMedical physicsMedicineNatural language processingInternal medicine

Abstract

fetched live from OpenAlex

Large language models generate plausible text responses to medical questions, but inaccurate responses pose significant risks in medical decision-making. Grading LLM outputs to determine the best model or answer is time-consuming and impractical in clinical settings; therefore, we introduce EVAL (Expert-of-Experts Verification and Alignment) to streamline this process and enhance LLM safety for upper gastrointestinal bleeding (UGIB). We evaluated OpenAI's GPT-3.5/4/4o/o1-preview, Anthropic's Claude-3-Opus, Meta's LLaMA-2 (7B/13B/70B), and Mistral AI's Mixtral (7B) across 27 configurations, including zero-shot baseline, retrieval-augmented generation, and supervised fine-tuning. EVAL uses similarity-based ranking and a reward model trained on human-graded responses for rejection sampling. Among the employed similarity metrics, Fine-Tuned ColBERT achieved the highest alignment with human performance across three separate datasets (ρ = 0.81-0.91). The reward model replicated human grading with 87.9% of cases across temperature settings and significantly improved accuracy through rejection sampling by 8.36% overall. EVAL offers scalable potential to assess accuracy for high-stakes medical decision-making.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.566
Threshold uncertainty score0.310

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.073
GPT teacher head0.421
Teacher spread0.347 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations6
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuenpj Digital MedicineSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207