MétaCan
Menu
Back to cohort
Record W4411447376 · doi:10.1109/icsc64641.2025.00032

MediTriR: A Triple-Driven Approach to Retrieval-Augmented Generation for Medical Question Answering Tasks

2025· article· en· W4411447376 on OpenAlexaff
Hongzhi Zhang, M. Omair Shafiq

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsCarleton University
Fundersnot available
KeywordsQuestion answeringComputer scienceInformation retrievalArtificial intelligenceNatural language processing

Abstract

fetched live from OpenAlex

Advances in large language models have driven progress in medical question-answering systems, but challenges remain in accuracy and relevance, especially in complex medical settings. To address this problem, we introduce MediTriR. This approach combines knowledge graph triples with a retrieval-augmented generation framework to enhance the performance of large language models in medical multiple-choice question-answering tasks. Our approach transforms the retrieved medical knowledge into structured triples and uses these triples for accurate information retrieval. Furthermore, we dynamically generate new triples based on the properties of triples to enrich the model's reasoning ability. The integration of retrieval-augmented generation enables more accurate and contextual answers by leveraging external medical triples. MediTriR is evaluated against pure large language model approaches using the MedMCQA and Medical QA datasets, showing better performance in terms of accuracy and relevance. These results highlight the potential of our approach to improve medical decision support and education.

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)0.004
metaresearch head score (Gemma)0.013
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.023

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.013
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.003
Bibliometrics0.0030.002
Science and technology studies0.0010.001
Scholarly communication0.0020.003
Open science0.0030.004
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0060.004

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 head0.030
GPT teacher head0.303
Teacher spread0.273 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207