EssayCBM: Rubric-Aligned Concept Bottleneck Models for Transparent Essay Grading
This addresses the problem of opaque grading systems for educators and students, offering a transparent and adjustable tool for essay assessment, though it is incremental in applying concept bottlenecks to this specific domain.
The paper tackles the lack of transparency in automated essay grading by introducing EssayCBM, a rubric-aligned concept bottleneck model that evaluates essays based on eight writing concepts like Thesis Clarity and Evidence Use, and it matches black-box performance while providing interpretable feedback.
Understanding how automated grading systems evaluate essays remains a significant challenge for educators and students, especially when large language models function as black boxes. We introduce EssayCBM, a rubric-aligned framework that prioritizes interpretability in essay assessment. Instead of predicting grades directly from text, EssayCBM evaluates eight writing concepts, such as Thesis Clarity and Evidence Use, through dedicated prediction heads on an encoder. These concept scores form a transparent bottleneck, and a lightweight network computes the final grade using only concepts. Instructors can adjust concept predictions and instantly view the updated grade, enabling accountable human-in-the-loop evaluation. EssayCBM matches black-box performance while offering actionable, concept-level feedback through an intuitive web interface.