Can MLLMs generate human-like feedback in grading multimodal short answers?

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sil, Pritam, Bhattacharyya, Pushpak, Goyal, Pawan, Ramakrishnan, Ganesh
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912879912943616
author Sil, Pritam
Bhattacharyya, Pushpak
Goyal, Pawan
Ramakrishnan, Ganesh
author_facet Sil, Pritam
Bhattacharyya, Pushpak
Goyal, Pawan
Ramakrishnan, Ganesh
contents In education, the traditional Automatic Short Answer Grading (ASAG) with feedback problem has focused primarily on evaluating text-only responses. However, real-world assessments often include multimodal responses containing both diagrams and text. To address this limitation, we introduce the Multimodal Short Answer Grading with Feedback (MMSAF) problem, which requires jointly evaluating textual and diagrammatic content while also providing explanatory feedback. Collecting data representative of such multimodal responses is challenging due to both scale and logistical constraints. To mitigate this, we develop an automated data generation framework that leverages LLM hallucinations to mimic common student errors, thereby constructing a dataset of 2,197 instances. We evaluate 4 Multimodal Large Language Models (MLLMs) across 3 STEM subjects, showing that MLLMs achieve accuracies of up to 62.5% in predicting answer correctness (correct/partially correct/incorrect) and up to 80.36% in assessing image relevance. This also includes a human evaluation with 9 annotators across 5 parameters, including a rubric-based approach. The rubrics also serve as a way to evaluate the feedback quality semantically rather than using overlap-based approaches. Our findings highlight which MLLMs are better suited for such tasks while also pointing out to drawbacks of the remaining MLLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19755
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can MLLMs generate human-like feedback in grading multimodal short answers?
Sil, Pritam
Bhattacharyya, Pushpak
Goyal, Pawan
Ramakrishnan, Ganesh
Artificial Intelligence
In education, the traditional Automatic Short Answer Grading (ASAG) with feedback problem has focused primarily on evaluating text-only responses. However, real-world assessments often include multimodal responses containing both diagrams and text. To address this limitation, we introduce the Multimodal Short Answer Grading with Feedback (MMSAF) problem, which requires jointly evaluating textual and diagrammatic content while also providing explanatory feedback. Collecting data representative of such multimodal responses is challenging due to both scale and logistical constraints. To mitigate this, we develop an automated data generation framework that leverages LLM hallucinations to mimic common student errors, thereby constructing a dataset of 2,197 instances. We evaluate 4 Multimodal Large Language Models (MLLMs) across 3 STEM subjects, showing that MLLMs achieve accuracies of up to 62.5% in predicting answer correctness (correct/partially correct/incorrect) and up to 80.36% in assessing image relevance. This also includes a human evaluation with 9 annotators across 5 parameters, including a rubric-based approach. The rubrics also serve as a way to evaluate the feedback quality semantically rather than using overlap-based approaches. Our findings highlight which MLLMs are better suited for such tasks while also pointing out to drawbacks of the remaining MLLMs.
title Can MLLMs generate human-like feedback in grading multimodal short answers?
topic Artificial Intelligence
url https://arxiv.org/abs/2412.19755