Large Language Models for Assisting American College Applications

TL;DR

EZCollegeApp is a large language model-based system designed to assist high-school students with college applications by structuring forms, grounding answers in official documents, and allowing human oversight, thus simplifying the complex application process.

Contribution

The paper introduces a novel mapping-first paradigm and system architecture that separates form understanding from answer generation, enhancing consistency and reliability in application assistance.

Findings

Effective form structuring and grounding in authoritative documents.

High human control and oversight in answer suggestions.

Open-source implementation available for broader use.

Abstract

American college applications require students to navigate fragmented admissions policies, repetitive and conditional forms, and ambiguous questions that often demand cross-referencing multiple sources. We present EZCollegeApp, a large language model (LLM)-powered system that assists high-school students by structuring application forms, grounding suggested answers in authoritative admissions documents, and maintaining full human control over final responses. The system introduces a mapping-first paradigm that separates form understanding from answer generation, enabling consistent reasoning across heterogeneous application portals. EZCollegeApp integrates document ingestion from official admissions websites, retrieval-augmented question answering, and a human-in-the-loop chatbot interface that presents suggestions alongside application fields without automated submission. We describe the system architecture, data pipeline, internal representations, security and privacy measures, and evaluation through automated testing and human quality assessment. Our source code is released on GitHub (https://github.com/ezcollegeapp-public/ezcollegeapp-public) to facilitate the broader impact of this work.