LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline
Generative AI and large language models (LLMs) are increasingly applied to question generation and automated assessment. However, deploying LLMs in preparation for high-stakes exams requires more than prompt engineering; it demands software pipelines that systematically ground mo...
ArXiv CS.AI
Source
Generated insight by OnAirToday AI
This research presents a crucial step towards reliable AI-driven educational assessment by grounding LLM judgments in official curricula. By creating verifiable and authorized context for LLMs, this pipeline fosters greater transparency and consistency in marking, moving beyond simple prompt engineering for high-stakes evaluations.
Get the day's AI news in one short email. Free.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.