EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational Assistants

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mittal, Meenakshi, Khare, Rishi, Miroyan, Mihran, Mitra, Chancharik, Norouzi, Narges
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917107493502976
author Mittal, Meenakshi
Khare, Rishi
Miroyan, Mihran
Mitra, Chancharik
Norouzi, Narges
author_facet Mittal, Meenakshi
Khare, Rishi
Miroyan, Mihran
Mitra, Chancharik
Norouzi, Narges
contents With the growing use of Large Language Model (LLM)-based Question-Answering (QA) systems in education, it is critical to evaluate their performance across individual pipeline components. In this work, we introduce {\model}, a modular function-calling LLM pipeline, and present a comprehensive evaluation along three key axes: function calling strategies, retrieval methods, and generative language models. Our framework enables fine-grained analysis by isolating and assessing each component. We benchmark function-calling performance across LLMs, compare our novel structure-aware retrieval method to vector-based and LLM-scoring baselines, and evaluate various LLMs for response synthesis. This modular approach reveals specific failure modes and performance patterns, supporting the development of interpretable and effective educational QA systems. Our findings demonstrate the value of modular function calling in improving system transparency and pedagogical alignment. Website and Supplementary Material: https://chancharikmitra.github.io/EduMod-LLM-website/
format Preprint
id arxiv_https___arxiv_org_abs_2511_21742
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational Assistants
Mittal, Meenakshi
Khare, Rishi
Miroyan, Mihran
Mitra, Chancharik
Norouzi, Narges
Computation and Language
Artificial Intelligence
With the growing use of Large Language Model (LLM)-based Question-Answering (QA) systems in education, it is critical to evaluate their performance across individual pipeline components. In this work, we introduce {\model}, a modular function-calling LLM pipeline, and present a comprehensive evaluation along three key axes: function calling strategies, retrieval methods, and generative language models. Our framework enables fine-grained analysis by isolating and assessing each component. We benchmark function-calling performance across LLMs, compare our novel structure-aware retrieval method to vector-based and LLM-scoring baselines, and evaluate various LLMs for response synthesis. This modular approach reveals specific failure modes and performance patterns, supporting the development of interpretable and effective educational QA systems. Our findings demonstrate the value of modular function calling in improving system transparency and pedagogical alignment. Website and Supplementary Material: https://chancharikmitra.github.io/EduMod-LLM-website/
title EduMod-LLM: A Modular Approach for Designing Flexible and Transparent Educational Assistants
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.21742