MétaCan
Menu
← Back to cohort
Record W4415641333 · doi:10.1101/2025.10.27.25338910

Human Evaluators vs. LLM-as-a-Judge: Toward Scalable, Real-Time Evaluation of GenAI in Global Health

2025· preprint· W4415641333 on OpenAlexaff
Gwydion Williams, Samuel Rutunda, Floris Nzabakira, Bilal A. Mateen

Bibliographic record

VenuemedRxiv · 2025
Typepreprint
Language
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsPrograms for Assessment of Technology in Health Research Institute
FundersBill and Melinda Gates Foundation
KeywordsContext (archaeology)EmpathyBottleneckReliability (semiconductor)Health careGold standard (test)OperationalizationGlobal health

Abstract

fetched live from OpenAlex

Abstract Evaluating the outputs of generative AI (GenAI) models in healthcare remains a significant bottleneck for the safe and scalable deployment of these tools. Human expert raters remain the gold standard for assessing the accuracy, contextual appropriateness, and empathy of AI-generated responses, but their assessments are costly, inconsistent, and difficult to scale. The concept of “LLM-as-a-judge” systems, i.e., AI models that can evaluate other AI outputs, has been recently proposed; however, their reliability in global health contexts remains untested. In this study, we systematically compared five LLM-judges and six expert human clinicians in evaluating both human- and AI-generated responses to real-world questions submitted by Rwandan community health workers seeking clinical decision support. Using an adapted version of the Med-PaLM 2 evaluation framework, evaluators scored responses across 11 criteria. Our results show that even the highest-performing LLM-judge (Claude-4.1-Opus) achieved human-equivalent evaluations on only four of eleven criteria. Constructing “LLM juries” to balance model-specific biases improved agreement on only one additional criterion. Some models were consistently overcritical (GPT-5) or overly lenient (Gemini-2.5-Pro). Moreover, performance and cost-effectiveness deteriorated substantially when moving from English to Kinyarwanda inputs. Overall, while LLM-judges demonstrate potential as scalable and internally consistent evaluators of GenAI outputs in healthcare, their sensitivity to linguistic and cultural context is a critical limitation. These findings underscore the need for further investment in scalable evaluation solutions, as well as potentially a fundamental rethink of how we approach the concept of “correctness” in clinical AI assessment (which is currently based on highly inconsistent expert clinician raters).

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.111
metaresearch head score (Gemma)0.202
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Evaluation · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.889
Threshold uncertainty score0.585

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1110.202
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.002
Scholarly communication0.0050.002
Open science0.0020.006
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0030.001

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 head0.174
GPT teacher head0.504
Teacher spread0.330 · 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 source (direct Gemma or distilled Codex), not a consensus.

Study designSimulation or modeling
DomainEvaluation
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

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuemedRxiv→Same topicArtificial Intelligence in Healthcare and Education→French-language works237,207→