23 citations · 32 across the 4 of their papers we have counts for
Showing physics.ed-phShow all
2 papers · 1 filter
physics.ed-ph2026
LLM-as-a-judge validity is strongly task-dependent across physics assessment formats
Will Yeadon, Tom Hardy, Paul Mackay +1
As large language models (LLMs) are increasingly considered for automated assessment and feedback, understanding when LLM marking is valid is essential. We evaluate LLM-as-a-judge…
physics.ed-ph2023★ 8 cited
Exploring Durham University Physics exams with Large Language Models
Will Yeadon, Douglas P. Halliday
The emergence of advanced Natural Language Processing (NLP) models like ChatGPT has raised concerns among universities regarding AI-driven exam completion. This paper provides a co…