# Embedding-Based Rankings of Educational Resources based on Learning Outcome Alignment: Benchmarking, Expert Validation, and Learner Performance

arXiv: https://arxiv.org/abs/2512.13658 · HTML: https://mlsanity.com/paper/2512.13658/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 34 references that are in the map.
- First posted on arXiv 15 Dec 2025.

## Builds on (most cited first, 7 of 7)

- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [When Large Language Models Meet Vector Databases: A Survey](https://mlsanity.com/paper/2402.01763/) (2024)
- [Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendations](https://mlsanity.com/paper/2403.03008/) (2024)
- [Can We Trust AI-Generated Educational Content? Comparative Analysis of Human and AI-Generated Learning Resources](https://mlsanity.com/paper/2306.10509/) (2023)
- [Extracting Topics from Open Educational Resources](https://mlsanity.com/paper/2006.11109/) (2020)

## Abstract (arXiv)

As the online learning landscape evolves, the need for personalization is increasingly evident. Although educational resources are burgeoning, educators face challenges selecting materials that both align with intended learning outcomes and address diverse learner needs. Large Language Models (LLMs) are attracting growing interest for their potential to create learning resources that better support personalization, but verifying coverage of intended outcomes still requires human alignment review, which is costly and limits scalability. We propose a framework that supports the cost-effective automation of evaluating alignment between educational resources and intended learning outcomes. Using human-generated materials, we benchmarked LLM-based text-embedding models and found that the most accurate model (Voyage) achieved 79% accuracy in detecting alignment. We then applied the optimal model to LLM-generated resources and, via expert evaluation, confirmed that it reliably assessed correspondence to intended outcomes (83% accuracy). Finally, in a three-group experiment with 360 learners, higher alignment scores were positively related to greater learning performance, chi-squared(2, N = 360) = 15.39, p < 0.001. These findings show that embedding-based alignment scores can facilitate scalable personalization by confirming alignment with learning outcomes, which allows teachers to focus on tailoring content to diverse learner needs.