# MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing

arXiv: https://arxiv.org/abs/2603.22289 · HTML: https://mlsanity.com/paper/2603.22289/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Deep Knowledge Tracing](https://mlsanity.com/paper/1506.05908/) (2015)
- [Context-Aware Attentive Knowledge Tracing](https://mlsanity.com/paper/2007.12324/) (2020)
- [A Self-Attentive model for Knowledge Tracing](https://mlsanity.com/paper/1907.06837/) (2019)
- [Dynamic Key-Value Memory Networks for Knowledge Tracing](https://mlsanity.com/paper/1611.08108/) (2016)
- [EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction](https://mlsanity.com/paper/1906.05658/) (2019)
- [Improving Interpretability of Deep Sequential Knowledge Tracing Models with Question-centric Cognitive Representations](https://mlsanity.com/paper/2302.06885/) (2023)
- [Language Model Can Do Knowledge Tracing: Simple but Effective Method to Integrate Language Model and Knowledge Tracing Task](https://mlsanity.com/paper/2406.02893/) (2024)
- [Interpretable Knowledge Tracing: Simple and Efficient Student Modeling with Causal Relations](https://mlsanity.com/paper/2112.11209/) (2021)
- [Forgetting-aware Linear Bias for Attentive Knowledge Tracing](https://mlsanity.com/paper/2309.14796/) (2023)
- [Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks](https://mlsanity.com/paper/2407.03624/) (2024)
- [Programming Knowledge Tracing: A Comprehensive Dataset and A New Model](https://mlsanity.com/paper/2112.08273/) (2021)
- [Auto-Evolve: Enhancing Large Language Model's Performance via Self-Reasoning Framework](https://mlsanity.com/paper/2410.06328/) (2024)
- [Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE](https://mlsanity.com/paper/2509.03626/) (2025)
- [A Systematic Review of Knowledge Tracing and Large Language Models in Education: Opportunities, Issues, and Future Research](https://mlsanity.com/paper/2412.09248/) (2024)
- [A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription](https://mlsanity.com/paper/2601.01708/) (2026)
- [Deep Trustworthy Knowledge Tracing](https://mlsanity.com/paper/1805.10768/) (2018)

## Built on by (most cited first, 1 of 1)

- [Can a System-One LLM Perform Knowledge Tracing When Few or No Learners Are Logged?](https://mlsanity.com/paper/2610.11135/) (2026)

## Abstract (arXiv)

Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack interpretability. Large Language Models (LLMs) offer strong reasoning capabilities but struggle with limited context windows and hallucinations. Furthermore, existing LLM-based methods typically require expensive fine-tuning, limiting scalability and adaptability to new data. We propose MERIT (Memory-Enhanced Retrieval for Interpretable Knowledge Tracing), a training-free framework combining frozen LLM reasoning with structured pedagogical memory. Rather than updating parameters, MERIT transforms raw interaction logs into an interpretable memory bank. The framework uses semantic denoising to categorize students into latent cognitive schemas and constructs a paradigm bank where representative error patterns are analyzed offline to generate explicit Chain-of-Thought (CoT) rationales. During inference, a hierarchical routing mechanism retrieves relevant contexts, while a logic-augmented module applies semantic constraints to calibrate predictions. By grounding the LLM in interpretable memory, MERIT achieves state-of-the-art performance on real-world datasets without gradient updates. This approach reduces computational costs and supports dynamic knowledge updates, improving the accessibility and transparency of educational diagnosis.