Instructional Goal-Aligned Question Generation for Student Evaluation in Virtual Lab Settings: How Closely Do LLMs Actually Align?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Knipper, R. Alexander, Dey, Indrani, Sarkar, Souvika, Narayanan, Hari, Puntambekar, Sadhana, Karmaker, Santu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908580674797568
author Knipper, R. Alexander
Dey, Indrani
Sarkar, Souvika
Narayanan, Hari
Puntambekar, Sadhana
Karmaker, Santu
author_facet Knipper, R. Alexander
Dey, Indrani
Sarkar, Souvika
Narayanan, Hari
Puntambekar, Sadhana
Karmaker, Santu
contents Virtual Labs offer valuable opportunities for hands-on, inquiry-based science learning, yet teachers often struggle to adapt them to fit their instructional goals. Third-party materials may not align with classroom needs, and developing custom resources can be time-consuming and difficult to scale. Recent advances in Large Language Models (LLMs) offer a promising avenue for addressing these limitations. In this paper, we introduce a novel alignment framework for instructional goal-aligned question generation, enabling teachers to leverage LLMs to produce simulation-aligned, pedagogically meaningful questions through natural language interaction. The framework integrates four components: instructional goal understanding via teacher-LLM dialogue, lab understanding via knowledge unit and relationship analysis, a question taxonomy for structuring cognitive and pedagogical intent, and the TELeR taxonomy for controlling prompt detail. Early design choices were informed by a small teacher-assisted case study, while our final evaluation analyzed over 1,100 questions from 19 open-source LLMs. With goal and lab understanding grounding questions in teacher intent and simulation context, the question taxonomy elevates cognitive demand (open-ended formats and relational types raise quality by 0.29-0.39 points), and optimized TELeR prompts enhance format adherence (80% parsability, >90% adherence). Larger models yield the strongest gains: parsability +37.1%, adherence +25.7%, and average quality +0.8 Likert points.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06411
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Instructional Goal-Aligned Question Generation for Student Evaluation in Virtual Lab Settings: How Closely Do LLMs Actually Align?
Knipper, R. Alexander
Dey, Indrani
Sarkar, Souvika
Narayanan, Hari
Puntambekar, Sadhana
Karmaker, Santu
Computation and Language
Virtual Labs offer valuable opportunities for hands-on, inquiry-based science learning, yet teachers often struggle to adapt them to fit their instructional goals. Third-party materials may not align with classroom needs, and developing custom resources can be time-consuming and difficult to scale. Recent advances in Large Language Models (LLMs) offer a promising avenue for addressing these limitations. In this paper, we introduce a novel alignment framework for instructional goal-aligned question generation, enabling teachers to leverage LLMs to produce simulation-aligned, pedagogically meaningful questions through natural language interaction. The framework integrates four components: instructional goal understanding via teacher-LLM dialogue, lab understanding via knowledge unit and relationship analysis, a question taxonomy for structuring cognitive and pedagogical intent, and the TELeR taxonomy for controlling prompt detail. Early design choices were informed by a small teacher-assisted case study, while our final evaluation analyzed over 1,100 questions from 19 open-source LLMs. With goal and lab understanding grounding questions in teacher intent and simulation context, the question taxonomy elevates cognitive demand (open-ended formats and relational types raise quality by 0.29-0.39 points), and optimized TELeR prompts enhance format adherence (80% parsability, >90% adherence). Larger models yield the strongest gains: parsability +37.1%, adherence +25.7%, and average quality +0.8 Likert points.
title Instructional Goal-Aligned Question Generation for Student Evaluation in Virtual Lab Settings: How Closely Do LLMs Actually Align?
topic Computation and Language
url https://arxiv.org/abs/2510.06411