BacPrep: An Experimental Platform for Evaluating LLM-Based Bacalaureat Assessment
This addresses the problem of exam preparation accessibility for Romanian students, but it is incremental as it focuses on experimental data collection rather than proven deployment.
The paper tackles the challenge of providing quality preparation and feedback for the Romanian Bacalaureat exam, especially for underserved students, by introducing BacPrep, an experimental online platform that uses Google's Gemini 2.0 Flash LLM with official exam questions and grading schemes to offer automated assessment and collect data for validation.
Accessing quality preparation and feedback for the Romanian Bacalaureat exam is challenging, particularly for students in remote or underserved areas. This paper introduces BacPrep, an experimental online platform exploring Large Language Model (LLM) potential for automated assessment, aiming to offer a free, accessible resource. Using official exam questions from the last 5 years, BacPrep employs one of Google's newest models, Gemini 2.0 Flash (released Feb 2025), guided by official grading schemes, to provide experimental feedback. Currently operational, its primary research function is collecting student solutions and LLM outputs. This focused dataset is vital for planned expert validation to rigorously evaluate the feasibility and accuracy of this cutting-edge LLM in the specific Bacalaureat context before reliable deployment. We detail the design, data strategy, status, validation plan, and ethics.