diagnostic-reasoning

Tag

Cards List
#diagnostic-reasoning

Prompting language influences diagnostic reasoning and accuracy of large language models

arXiv cs.CL · 2026-05-20 Cached

This study evaluates how prompting language (English vs. French) affects diagnostic reasoning and accuracy across five LLMs using 180 clinical vignettes, finding that most models perform significantly better in English, with o3 being the only exception.

0 favorites 0 likes
#diagnostic-reasoning

Experiments or Outcomes? Probing Scientific Feasibility in Large Language Models

arXiv cs.CL · 2026-04-22 Cached

UMBC researchers show LLMs judge scientific claim feasibility better when given outcome data than experiment descriptions, and that incomplete experimental context can hurt accuracy.

0 favorites 0 likes
← Back to home

Submit Feedback