Large Language Models for Assisting American College Applications
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.
Cite
@article{arxiv.2602.15850,
title = {Large Language Models for Assisting American College Applications},
author = {Zhengliang Liu and Weihang You and Peng Shu and Junhao Chen and Yi Pan and Hanqi Jiang and Yiwei Li and Zhaojun Ding and Chao Cao and Xinliang Li and Yifan Zhou and Ruidong Zhang and Shaochen Xu and Wei Ruan and Huaqin Zhao and Dajiang Zhu and Tianming Liu},
journal= {arXiv preprint arXiv:2602.15850},
year = {2026}
}