PathBuilder: A Quality-Controlled LLM System for Personalized Learning Pathways
Jasper Meynard Arana Adamson University, John Andrew Mañacop, John Allen Manacop Asian Institute of Management, Roy Andrew Garcia Makarius Smart Learning, Keith Rick Piniera Asian Institute of Management, Kristine Ann M. Carandang Professional Regulation Commission, Asian Institute of Management and Asian Institute of Management, Ethan Robert Casin, Christian Alis Asian Institute of Management 等 9 位作者
原文摘要
Large language models (LLMs) enable scalable content generation for personalized learning, but reliability and pedagogical alignment remain open challenges. We present PathBuilder, a web-based system that integrates expert-validated assessment, retrieval-augmented generation (RAG), and an LLM-as-a-Judge validation loop within a closed instructional pipeline. The system uses a 17,758-item curriculum-aligned question bank, including 1,018 expert-approved LLM-generated items, to construct diagnostic and post-tests for fine-grained learner profiling. In a real-world deployment with 179 registered users (75 matched learners), PathBuilder achieved a mean absolute gain of 37.9 percentage points, Hake’s normalized gain of 0.760, and a large effect size (Cohen’s d = 0.98). A controlled study of the judge mechanism showed consistent high-quality instructional outputs with a 100% threshold pass rate. These results demonstrate that structured curriculum alignment combined with retrieval grounding and automated validation can support reliable LLM-based personalization in deployed learning systems. A live demonstration of PathBuilder is available at https://demo.pathbuilderedu.com.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) · 2026 · 正式发表