Pith. sign in

REVIEW 1 cited by

Automated Feedback in Math Education: A Comparative Analysis of LLMs for Open-Ended Responses

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.08910 v1 pith:SZVDVY3Z submitted 2024-10-29 cs.CY cs.AIcs.LG

classification cs.CYcs.AIcs.LG
keywords feedbackmodelllmsmathresponsesautomatedstudenteffectiveness
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The effectiveness of feedback in enhancing learning outcomes is well documented within Educational Data Mining (EDM). Various prior research has explored methodologies to enhance the effectiveness of feedback. Recent developments in Large Language Models (LLMs) have extended their utility in enhancing automated feedback systems. This study aims to explore the potential of LLMs in facilitating automated feedback in math education. We examine the effectiveness of LLMs in evaluating student responses by comparing 3 different models: Llama, SBERT-Canberra, and GPT4 model. The evaluation requires the model to provide both a quantitative score and qualitative feedback on the student's responses to open-ended math problems. We employ Mistral, a version of Llama catered to math, and fine-tune this model for evaluating student responses by leveraging a dataset of student responses and teacher-written feedback for middle-school math problems. A similar approach was taken for training the SBERT model as well, while the GPT4 model used a zero-shot learning approach. We evaluate the model's performance in scoring accuracy and the quality of feedback by utilizing judgments from 2 teachers. The teachers utilized a shared rubric in assessing the accuracy and relevance of the generated feedback. We conduct both quantitative and qualitative analyses of the model performance. By offering a detailed comparison of these methods, this study aims to further the ongoing development of automated feedback systems and outlines potential future directions for leveraging generative LLMs to create more personalized learning experiences.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Combining model tracing and constraint-based modeling for multistep strategy diagnoses

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A tutoring-system method that combines model tracing and constraints correctly classified 140 sampled student steps in quadratic equation solving as strategy-following or deviating.

Pith tools