Domain-Grounded Evaluation of LLMs in International Student Knowledge

TL;DR

This paper evaluates the reliability of large language models in advising international students on high-stakes questions, focusing on accuracy, hallucinations, and domain coverage using real-world questions from an EdTech platform.

Contribution

It introduces a domain-grounded evaluation protocol for assessing LLMs in educational advising, emphasizing accuracy, hallucination detection, and domain coverage analysis.

Findings

Models vary in accuracy and hallucination rates.

Common failure modes include incomplete and off-topic answers.

The protocol helps identify dependable models for educational use.

Abstract

Large language models (LLMs) are increasingly used to answer high-stakes study-abroad questions about admissions, visas, scholarships, and eligibility. Yet it remains unclear how reliably they advise students, and how often otherwise helpful answers drift into unsupported claims (``hallucinations''). This work provides a clear, domain-grounded overview of how current LLMs behave in this setting. Using realistic questions set drawn from ApplyBoard's advising workflows -- an EdTech platform that supports students from discovery to enrolment -- we evaluate two essentials side by side: accuracy (is the information correct and complete?) and hallucination (does the model add content not supported by the question or domain evidence). These questions are categorized by domain scope which can be a single-domain or multi-domain -- when it must integrate evidence across areas such as admissions, visas, and scholarships. To reflect real advising quality, we grade answers with a simple rubric which is correct, partial, or wrong. The rubric is domain-coverage-aware: an answer can be partial if it addresses only a subset of the required domains, and it can be over-scoped if it introduces extra, unnecessary domains; both patterns are captured in our scoring as under-coverage or reduced relevance/hallucination. We also report measures of faithfulness and answer relevance, alongside an aggregate hallucination score, to capture relevance and usefulness. All models are tested with the same questions for a fair, head-to-head comparison. Our goals are to: (1) give a clear picture of which models are most dependable for study-abroad advising, (2) surface common failure modes -- where answers are incomplete, off-topic, or unsupported, and (3) offer a practical, reusable protocol for auditing LLMs before deployment in education and advising contexts.