Get Started
Research questionHow can LLMs assess academic proposals and peer feedback with pedagogically grounded scores?Academic writing assessment spans students’ proposals and the feedback they provide, yet these materials and human judgments are rarely linked in a public resource. The connection between drafting, feedback, and revision also makes educationally meaningful automated assessment difficult to study.
AI
Evaluation & Benchmarks
Natural Language Processing
Latest papersRecent research connected to this question, newest first.Exposía: Teaching and Assessment of Academic Writing Skills for Research Project Proposals and Peer FeedbackExposía provides proposals, peer and instructor comments, free-text reviews, and human scores from a Computer Science course on scientific work. It supports benchmarking LLM scoring for proposals and student reviews; the reported evidence compares closed-source with open-weight models and examines prompting that scores multiple writing aspects together.research paper · Sep 2, 2026
Related questions
How can LLM judges produce reliable, unbiased scores for subjective, interdependent multi-step creativity tasks?How can LLM graders assign accurate marks while grounding each judgment in rubrics and student-answer evidence?Can user feedback reliably guide LLM revisions if LLM judges overlook the resulting improvements?How can we tell whether agreement among LLM judges reflects human alignment or shared blind spots?
Home
Topics
Search
Library