Jove
Visualize
Contact Us

Related Concept Videos

Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cross-lingual transfer with multilingual language models for influenza-like-illness detection in social media texts.

npj digital public health·2026
Same author

Determining suicide risk in an adolescent population: Questionnaire-based approaches.

Health informatics journal·2026
Same author

Explanatory argument extraction of correct answers in resident medical exams.

Artificial intelligence in medicine·2024
Same author

Cause of Death estimation from Verbal Autopsies: Is the Open Response redundant or synergistic?

Artificial intelligence in medicine·2023
Same author

Neural negated entity recognition in Spanish electronic health records.

Journal of biomedical informatics·2020
Same author

Recent advances in Swedish and Spanish medical entity recognition in clinical texts using deep neural approaches.

BMC medical informatics and decision making·2019
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 5, 2026

Executing Complexity-Increasing Queries in Relational MySQL and NoSQL MongoDB and EXist Size-Growing ISO/EN 13606 Standardized EHR Databases
07:26

Executing Complexity-Increasing Queries in Relational MySQL and NoSQL MongoDB and EXist Size-Growing ISO/EN 13606 Standardized EHR Databases

Published on: March 19, 2018

9.3K

MedExpQA: Multilingual benchmarking of Large Language Models for Medical Question Answering.

Iñigo Alonso1, Maite Oronoz1, Rodrigo Agerri1

  • 1HiTZ Center - Ixa, University of the Basque Country UPV/EHU, Spain.

Artificial Intelligence in Medicine
|August 9, 2024
PubMed
Summary

Large Language Models show promise in medical AI but struggle with outdated information and hallucinations. A new multilingual benchmark, MedExpQA, reveals significant performance gaps, especially for non-English languages.

Keywords:
Large Language ModelsMedical Question AnsweringMultilingualityNatural Language ProcessingRetrieval Augmented Generation

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

533

Related Experiment Videos

Last Updated: Jul 5, 2026

Executing Complexity-Increasing Queries in Relational MySQL and NoSQL MongoDB and EXist Size-Growing ISO/EN 13606 Standardized EHR Databases
07:26

Executing Complexity-Increasing Queries in Relational MySQL and NoSQL MongoDB and EXist Size-Growing ISO/EN 13606 Standardized EHR Databases

Published on: March 19, 2018

9.3K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

533

Area of Science:

  • Artificial Intelligence in Medicine
  • Natural Language Processing
  • Medical Education Technology

Background:

  • Large Language Models (LLMs) demonstrate potential for AI-driven medical decision support, achieving high scores on medical licensing exams.
  • Current LLMs face challenges including outdated knowledge, content hallucination, and a lack of explainability in medical question answering.
  • Existing benchmarks lack gold-standard explanations, hindering the evaluation of LLM reasoning capabilities.

Purpose of the Study:

  • Introduce MedExpQA, the first multilingual benchmark for evaluating LLMs in medical question answering using medical exam data.
  • Incorporate gold explanations from medical doctors for correct and incorrect options to enable reasoning assessment.
  • Address the neglected area of LLM benchmarking in languages other than English.

Main Methods:

  • Developed MedExpQA, a novel multilingual benchmark dataset derived from medical examinations.
  • Included expert-written gold explanations for all exam options.
  • Conducted comprehensive multilingual experiments utilizing LLMs with and without Retrieval Augmented Generation (RAG).

Main Results:

  • LLM performance in medical question answering reached approximately 75% accuracy in English.
  • Accuracy dropped by 10 points for languages other than English, highlighting significant multilingual disparities.
  • Even with state-of-the-art RAG methods, integrating readily available medical knowledge remains challenging.

Conclusions:

  • MedExpQA provides a crucial resource for evaluating and improving LLMs in medical question answering.
  • Current LLMs require substantial advancements to meet the quality standards for reliable medical applications, particularly in multilingual contexts.
  • Further research is needed to effectively incorporate and leverage medical knowledge for enhanced LLM performance.