# Explainable Automatic Grading with Neural Additive Models

arXiv: https://arxiv.org/abs/2405.00489 · HTML: https://mlsanity.com/paper/2405.00489/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 1 May 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Explaining black box text modules in natural language with language models](https://mlsanity.com/paper/2305.09863/) (2023)
- [Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers](https://mlsanity.com/paper/2204.03503/) (2022)
- [Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoring](https://mlsanity.com/paper/2209.10070/) (2022)
- [Structural Neural Additive Models: Enhanced Interpretable Machine Learning](https://mlsanity.com/paper/2302.09275/) (2023)
- [Neural Additive Models for Nowcasting](https://mlsanity.com/paper/2205.10020/) (2022)

## Built on by (most cited first, 3 of 3)

- [A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization](https://mlsanity.com/paper/2410.02165/) (2024)
- [Ratas framework: A comprehensive genai-based approach to rubric-based marking of real-world textual exams](https://mlsanity.com/paper/2505.23818/) (2025)
- [Interpretability from the Ground Up: Stakeholder-Centric Design of Automated Scoring in Educational Assessments](https://mlsanity.com/paper/2511.17069/) (2025)

## Abstract (arXiv)

The use of automatic short answer grading (ASAG) models may help alleviate the time burden of grading while encouraging educators to frequently incorporate open-ended items in their curriculum. However, current state-of-the-art ASAG models are large neural networks (NN) often described as "black box", providing no explanation for which characteristics of an input are important for the produced output. This inexplicable nature can be frustrating to teachers and students when trying to interpret, or learn from an automatically-generated grade. To create a powerful yet intelligible ASAG model, we experiment with a type of model called a Neural Additive Model that combines the performance of a NN with the explainability of an additive model. We use a Knowledge Integration (KI) framework from the learning sciences to guide feature engineering to create inputs that reflect whether a student includes certain ideas in their response. We hypothesize that indicating the inclusion (or exclusion) of predefined ideas as features will be sufficient for the NAM to have good predictive power and interpretability, as this may guide a human scorer using a KI rubric. We compare the performance of the NAM with another explainable model, logistic regression, using the same features, and to a non-explainable neural model, DeBERTa, that does not require feature engineering.