skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on July 12, 2026

Title: A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization
Open-text responses provide researchers and educators with rich, nuanced insights that multiple-choice questions cannot capture. When reliably assessed, such responses have the potential to enhance teaching and learning. However, scaling and consistently capturing these nuances remain significant challenges, limiting the widespread use of open-text questions in educational research and assessments. In this paper, we introduce and evaluate GradeOpt, a unified multiagent automatic short-answer grading (ASAG) framework that leverages large language models (LLMs) as graders for short-answer responses. 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. To assess GradeOpt's effectiveness, we conducted experiments on two representative ASAG datasets, which include items designed to capture key aspects of teachers' pedagogical knowledge and students' learning progress. Our results demonstrate that GradeOpt consistently outperforms representative baselines in both grading accuracy and alignment with human evaluators across different knowledge domains. Finally, comprehensive ablation studies validate the contributions of GradeOpt's individual components, confirming their impact on overall performance.  more » « less
Award ID(s):
2200757
PAR ID:
10621106
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ; ;
Editor(s):
Mills, Caitlin; Alexandron, Giora; Taibi, Davide; Lo_Bosco, Giosuè; Paquette, Luc
Publisher / Repository:
International Educational Data Mining Society
Date Published:
ISBN:
978-1-7336736-6-2
Format(s):
Medium: X
Right(s):
Creative Commons Attribution 4.0 International
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, s, Proceedings of the 15th International Conference on Educational Data Mining)
    Mitrovic, A; Bosch, N. (Ed.)
    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-theart 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 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 on 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) outperform existing approaches, especially for new questions that are not seen during training. 
    more » « less
  2. ; ; ; (, Proceedings of the 15th International Conference on Educational Data Mining, International Educational Data Mining Society)
    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-theart 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 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 on 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) outperform existing approaches, especially for new questions that are not seen during training. 
    more » « less
  3. ; ; ; (, Proceedings from the 15th International Conference on Educational Data Mining)
    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-theart 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 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 on 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) outperform existing approaches, especially for new questions that are not seen during training. 
    more » « less
  4. ; ; ; (, Proceedings of the 15th International Conference on Educational Data Mining)
    Mitrovic, A; Bosch, N (Ed.)
    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-theart 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 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 on 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) outperform existing approaches, especially for new questions that are not seen during training. 
    more » « less
  5. ; ; ; (, AIED 2022)
    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-theart 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 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 on 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) outperform existing approaches, especially for new questions that are not seen during training. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email