Researchers have developed ArguLens, an open-source system designed for automated essay scoring (AES) and generating feedback. Unlike traditional AES systems that provide only a holistic score, ArguLens breaks down the scoring process into three distinct, locally deployable components: a discourse-move classifier, a feature-based scorer, and a feedback generator. This modular approach aims to offer more interpretable evidence for scores and address data privacy concerns associated with closed APIs. The system, built using models like Qwen2.5-7B-Instruct and Qwen2.5-14BInstruct, has demonstrated strong performance in its classification and scoring modules. AI
IMPACT Provides a more transparent and privacy-preserving alternative for automated essay scoring, potentially improving educational feedback systems.
RANK_REASON The item describes a research paper detailing an open-source system for automated essay scoring. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
