The rise of artificial intelligence (AI) technologies, particularly large language models (LLMs), has brought significant advancements to the field of education. Among various applications, automatic short answer grading (ASAG), which focuses on evaluating open-ended textual responses, has seen remarkable progress with the introduction of LLMs. These models not only enhance grading performance compared to traditional ASAG approaches but also move beyond simple comparisons with predefined "golden" answers, enabling more sophisticated grading scenarios, such as rubric-based evaluation. However, existing LLM-powered methods still face challenges in achieving human-level grading performance in rubric-based assessments due to their reliance on fully automated approaches. In this work, we explore the potential of LLMs in ASAG tasks by leveraging their interactive capabilities through a human-in-the-loop (HITL) approach. Our proposed framework, GradeHITL, utilizes the generative properties of LLMs to pose questions to human experts, incorporating their insights to refine grading rubrics dynamically. This adaptive process significantly improves grading accuracy, outperforming existing methods and bringing ASAG closer to human-level evaluation.
Providing evaluations to student work is a critical component of effective student learning, and automating its process can significantly reduce the workload on human graders. Automatic Short Answer Grading (ASAG) systems, enabled by advancements in Large Language Models (LLMs), offer a promising solution for assessing and providing instant feedback for open-ended student responses. In this paper, we present an ASAG pipeline leveraging state-of-the-art LLMs. Our new LLM-based ASAG pipeline achieves better performances than existing custom-built models on the same datasets. We also compare the grading performance of three OpenAI models: GPT-4, GPT-4o, and o1-preview. Our results demonstrate that GPT-4o achieves the best balance between accuracy and cost-effectiveness. On the other hand, o1-preview, despite higher accuracy, exhibits a larger variance in error that makes it less practical for classroom use. We investigate the effects of incorporating instructor-graded examples into prompts using no examples, random selection, and Retrieval-Augmented Generation (RAG)-based selection strategies. Our findings indicate that providing graded examples enhances grading accuracy, with RAG-based selection outperforming random selection. Additionally, integrating grading rubrics improves accuracy by offering a structured standard for evaluation.
Assessments play a vital role in a student's learning process. This is because they provide valuable feedback crucial to a student's growth. Such assessments contain questions with open-ended responses, which are difficult to grade at scale. These responses often require students to express their understanding through textual and visual elements together as a unit. In order to develop scalable assessment tools for such questions, one needs multimodal LLMs having strong comparative reasoning capabilities across multiple modalities. Thus, to facilitate research in this area, we propose the Multimodal Short Answer grading with Feedback (MMSAF) problem along with a dataset of 2,197 data points. Additionally, we provide an automated framework for generating such datasets. As per our evaluations, existing Multimodal Large Language Models (MLLMs) could predict whether an answer is correct, incorrect or partially correct with an accuracy of 55%. Similarly, they could predict whether the image provided in the student's answer is relevant or not with an accuracy of 75%. As per human experts, Pixtral was more aligned towards human judgement and values for biology and ChatGPT for physics and chemistry and achieved a score of 4 or more out of 5 in most parameters.
Open-ended short-answer questions (SAGs) have been widely recognized as a powerful tool for providing deeper insights into learners' responses in the context of learning analytics (LA). However, SAGs often present challenges in practice due to the high grading workload and concerns about inconsistent assessments. With recent advancements in natural language processing (NLP), automatic short-answer grading (ASAG) offers a promising solution to these challenges. Despite this, current ASAG algorithms are often limited in generalizability and tend to be tailored to specific questions. In this paper, we propose a unified multi-agent ASAG framework, GradeOpt, which leverages large language models (LLMs) as graders for SAGs. More importantly, GradeOpt incorporates two additional LLM-based agents - the reflector and the refiner - into the multi-agent system. This enables GradeOpt to automatically optimize the original grading guidelines by performing self-reflection on its errors. Through experiments on a challenging ASAG task, namely the grading of pedagogical content knowledge (PCK) and content knowledge (CK) questions, GradeOpt demonstrates superior performance in grading accuracy and behavior alignment with human graders compared to representative baselines. Finally, comprehensive ablation studies confirm the effectiveness of the individual components designed in GradeOpt.
In recent years, there has been a growing interest in using Artificial Intelligence (AI) to automate student assessment in education. Among different types of assessments, summative assessments play a crucial role in evaluating a student's understanding level of a course. Such examinations often involve short-answer questions. However, grading these responses and providing meaningful feedback manually at scale is both time-consuming and labor-intensive. Feedback is particularly important, as it helps students recognize their strengths and areas for improvement. Despite the importance of this task, there is a significant lack of publicly available datasets that support automatic short-answer grading with feedback generation. To address this gap, we introduce Engineering Short Answer Feedback (EngSAF), a dataset designed for automatic short-answer grading with feedback. The dataset covers a diverse range of subjects, questions, and answer patterns from multiple engineering domains and contains ~5.8k data points. We incorporate feedback into our dataset by leveraging the generative capabilities of state-of-the-art large language models (LLMs) using our Label-Aware Synthetic Feedback Generation (LASFG) strategy. This paper underscores the importance of enhanced feedback in practical educational settings, outlines dataset annotation and feedback generation processes, conducts a thorough EngSAF analysis, and provides different LLMs-based zero-shot and finetuned baselines for future comparison. The best-performing model (Mistral-7B) achieves an overall accuracy of 75.4% and 58.7% on unseen answers and unseen question test sets, respectively. Additionally, we demonstrate the efficiency and effectiveness of our ASAG system through its deployment in a real-world end-semester exam at a reputed institute.
We explore the use of deep reinforcement learning to audit an automatic short answer grading (ASAG) model. Automatic grading may decrease the time burden of rating open-ended items for educators, but a lack of robust evaluation methods for these models can result in uncertainty of their quality. Current state-of-the-art ASAG models are configured to match human ratings from a training set, and researchers typically assess their quality with accuracy metrics that signify agreement between model and human scores. In this paper, we show that a high level of agreement to human ratings does not give sufficient evidence that an ASAG model is infallible. We train a reinforcement learning agent to revise student responses with the objective of achieving a high rating from an automatic grading model in the least number of revisions. By analyzing the agent's revised responses that achieve a high grade from the ASAG model but would not be considered a high scoring responses according to a scoring rubric, we discover ways in which the automated grader can be exploited, exposing shortcomings in the grading model.
The grading of open-ended questions is a high-effort, high-impact task in education. Automating this task promises a significant reduction in workload for education professionals, as well as more consistent grading outcomes for students, by circumventing human subjectivity and error. While recent breakthroughs in AI technology might facilitate such automation, this has not been demonstrated at scale. It this paper, we introduce a novel automatic short answer grading (ASAG) system. The system is based on a fine-tuned open-source transformer model which we trained on large set of exam data from university courses across a large range of disciplines. We evaluated the trained model's performance against held-out test data in a first experiment and found high accuracy levels across a broad spectrum of unseen questions, even in unseen courses. We further compared the performance of our model with that of certified human domain experts in a second experiment: we first assembled another test dataset from real historical exams - the historic grades contained in that data were awarded to students in a regulated, legally binding examination process; we therefore considered them as ground truth for our experiment. We then asked certified human domain experts and our model to grade the historic student answers again without disclosing the historic grades. Finally, we compared the hence obtained grades with the historic grades (our ground truth). We found that for the courses examined, the model deviated less from the official historic grades than the human re-graders - the model's median absolute error was 44 % smaller than the human re-graders', implying that the model is more consistent than humans in grading. These results suggest that leveraging AI enhanced grading can reduce human subjectivity, improve consistency and thus ultimately increase fairness.
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.
Grading short answer questions automatically with interpretable reasoning behind the grading decision is a challenging goal for current transformer approaches. Justification cue detection, in combination with logical reasoners, has shown a promising direction for neuro-symbolic architectures in ASAG. But, one of the main challenges is the requirement of annotated justification cues in the students' responses, which only exist for a few ASAG datasets. To overcome this challenge, we contribute (1) a weakly supervised annotation procedure for justification cues in ASAG datasets, and (2) a neuro-symbolic model for explainable ASAG based on justification cues. Our approach improves upon the RMSE by 0.24 to 0.3 compared to the state-of-the-art on the Short Answer Feedback dataset in a bilingual, multi-domain, and multi-question training setup. This result shows that our approach provides a promising direction for generating high-quality grades and accompanying explanations for future research in ASAG and educational NLP.
Automatic short answer grading is an important research direction in the exploration of how to use artificial intelligence (AI)-based tools to improve education. Current state-of-the-art approaches use neural language models to create vectorized representations of students responses, followed by classifiers to predict the score. However, these approaches have several key limitations, including i) they use pre-trained language models that are not well-adapted to educational subject domains and/or student-generated text and ii) they almost always train one model per question, ignoring the linkage across a question and result in a significant model storage problem due to the size of advanced language models. In this paper, we study the problem of automatic short answer grading for students' responses to math questions and propose a novel framework for this task. First, we use MathBERT, a variant of the popular language model BERT adapted to mathematical content, as our base model and fine-tune it for the downstream task of student response grading. Second, we use an in-context learning approach that provides scoring examples as input to the language model to provide additional context information and promote generalization to previously unseen questions. We evaluate our framework on a real-world dataset of student responses to open-ended math questions and show that our framework (often significantly) outperforms existing approaches, especially for new questions that are not seen during training.
Automatic grading models are valued for the time and effort saved during the instruction of large student bodies. Especially with the increasing digitization of education and interest in large-scale standardized testing, the popularity of automatic grading has risen to the point where commercial solutions are widely available and used. However, for short answer formats, automatic grading is challenging due to natural language ambiguity and versatility. While automatic short answer grading models are beginning to compare to human performance on some datasets, their robustness, especially to adversarially manipulated data, is questionable. Exploitable vulnerabilities in grading models can have far-reaching consequences ranging from cheating students receiving undeserved credit to undermining automatic grading altogether - even when most predictions are valid. In this paper, we devise a black-box adversarial attack tailored to the educational short answer grading scenario to investigate the grading models' robustness. In our attack, we insert adjectives and adverbs into natural places of incorrect student answers, fooling the model into predicting them as correct. We observed a loss of prediction accuracy between 10 and 22 percentage points using the state-of-the-art models BERT and T5. While our attack made answers appear less natural to humans in our experiments, it did not significantly increase the graders' suspicions of cheating. Based on our experiments, we provide recommendations for utilizing automatic grading systems more safely in practice.
Automatic Short Answer Grading (ASAG) is the process of grading the student answers by computational approaches given a question and the desired answer. Previous works implemented the methods of concept mapping, facet mapping, and some used the conventional word embeddings for extracting semantic features. They extracted multiple features manually to train on the corresponding datasets. We use pretrained embeddings of the transfer learning models, ELMo, BERT, GPT, and GPT-2 to assess their efficiency on this task. We train with a single feature, cosine similarity, extracted from the embeddings of these models. We compare the RMSE scores and correlation measurements of the four models with previous works on Mohler dataset. Our work demonstrates that ELMo outperformed the other three models. We also, briefly describe the four transfer learning models and conclude with the possible causes of poor results of transfer learning models.
Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a cost-effective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads. However, ASAG is a very challenging task due to two reasons: (1) student answers are made up of free text which requires a deep semantic understanding; and (2) the questions are usually open-ended and across many domains in K-12 scenarios. In this paper, we propose a generalized end-to-end ASAG learning framework which aims to (1) autonomously extract linguistic information from both student and reference answers; and (2) accurately model the semantic relations between free-text student and reference answers in open-ended domain. The proposed ASAG model is evaluated on a large real-world K-12 dataset and can outperform the state-of-the-art baselines in terms of various evaluation metrics.
One of the fundamental challenges towards building any intelligent tutoring system is its ability to automatically grade short student answers. A typical automatic short answer grading system (ASAG) grades student answers across multiple domains (or subjects). Grading student answers requires building a supervised machine learning model that evaluates the similarity of the student answer with the reference answer(s). We observe that unlike typical textual similarity or entailment tasks, the notion of similarity is not universal here. On one hand, para-phrasal constructs of the language can indicate similarity independent of the domain. On the other hand, two words, or phrases, that are not strict synonyms of each other, might mean the same in certain domains. Building on this observation, we propose JMD-ASAG, the first joint multidomain deep learning architecture for automatic short answer grading that performs domain adaptation by learning generic and domain-specific aspects from the limited domain-wise training data. JMD-ASAG not only learns the domain-specific characteristics but also overcomes the dependence on a large corpus by learning the generic characteristics from the task-specific data itself. On a large-scale industry dataset and a benchmarking dataset, we show that our model performs significantly better than existing techniques which either learn domain-specific models or adapt a generic similarity scoring model from a large corpus. Further, on the benchmarking dataset, we report state-of-the-art results against all existing non-neural and neural models.
Automatic grading is not a new approach but the need to adapt the latest technology to automatic grading has become very important. As the technology has rapidly became more powerful on scoring exams and essays, especially from the 1990s onwards, partially or wholly automated grading systems using computational methods have evolved and have become a major area of research. In particular, the demand of scoring of natural language responses has created a need for tools that can be applied to automatically grade these responses. In this paper, we focus on the concept of automatic grading of short answer questions such as are typical in the UK GCSE system, and providing useful feedback on their answers to students. We present experimental results on a dataset provided from the introductory computer science class in the University of North Texas. We first apply standard data mining techniques to the corpus of student answers for the purpose of measuring similarity between the student answers and the model answer. This is based on the number of common words. We then evaluate the relation between these similarities and marks awarded by scorers. We then consider an approach that groups student answers into clusters. Each cluster would be awarded the same mark, and the same feedback given to each answer in a cluster. In this manner, we demonstrate that clusters indicate the groups of students who are awarded the same or the similar scores. Words in each cluster are compared to show that clusters are constructed based on how many and which words of the model answer have been used. The main novelty in this paper is that we design a model to predict marks based on the similarities between the student answers and the model answer.
Automatic short answer grading (ASAG) techniques are designed to automatically assess short answers to questions in natural language, having a length of a few words to a few sentences. Supervised ASAG techniques have been demonstrated to be effective but suffer from a couple of key practical limitations. They are greatly reliant on instructor provided model answers and need labeled training data in the form of graded student answers for every assessment task. To overcome these, in this paper, we introduce an ASAG technique with two novel features. We propose an iterative technique on an ensemble of (a) a text classifier of student answers and (b) a classifier using numeric features derived from various similarity measures with respect to model answers. Second, we employ canonical correlation analysis based transfer learning on a common feature representation to build the classifier ensemble for questions having no labelled data. The proposed technique handsomely beats all winning supervised entries on the SCIENTSBANK dataset from the Student Response Analysis task of SemEval 2013. Additionally, we demonstrate generalizability and benefits of the proposed technique through evaluation on multiple ASAG datasets from different subject topics and standards.