# Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing

arXiv: https://arxiv.org/abs/2410.12872 · HTML: https://mlsanity.com/paper/2410.12872/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 13 of 13)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Deep Knowledge Tracing](https://mlsanity.com/paper/1506.05908/) (2015)
- [Context-Aware Attentive Knowledge Tracing](https://mlsanity.com/paper/2007.12324/) (2020)
- [Dynamic Key-Value Memory Networks for Knowledge Tracing](https://mlsanity.com/paper/1611.08108/) (2016)
- [EdNet: A Large-Scale Hierarchical Dataset in Education](https://mlsanity.com/paper/1912.03072/) (2019)
- [TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction](https://mlsanity.com/paper/2310.15556/) (2023)
- [Knowledge Query Network: How Knowledge Interacts with Skills](https://mlsanity.com/paper/1908.02146/) (2019)
- [Towards Modeling Learner Performance with Large Language Models](https://mlsanity.com/paper/2403.14661/) (2024)
- [Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge](https://mlsanity.com/paper/2104.04034/) (2021)
- [CLST: Cold-Start Mitigation in Knowledge Tracing by Aligning a Generative Language Model as a Students' Knowledge Tracer](https://mlsanity.com/paper/2406.10296/) (2024)
- [Option Tracing: Beyond Correctness Analysis in Knowledge Tracing](https://mlsanity.com/paper/2104.09043/) (2021)
- [No Task Left Behind: Multi-Task Learning of Knowledge Tracing and Option Tracing for Better Student Assessment](https://mlsanity.com/paper/2204.14006/) (2022)

## Built on by (most cited first, 2 of 2)

- [A Training-Free Large Reasoning Model-based Knowledge Tracing Framework for Unified Prediction and Prescription](https://mlsanity.com/paper/2601.01708/) (2026)
- [Can a System-One LLM Perform Knowledge Tracing When Few or No Learners Are Logged?](https://mlsanity.com/paper/2610.11135/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have recently emerged as promising tools for knowledge tracing (KT) due to their strong reasoning and generalization abilities. While recent LLM-based KT methods have proposed new prompt formats, they struggle to represent the full interaction histories of example learners within a single prompt during in-context learning (ICL), resulting in limited scalability and high computational cost under token constraints. In this work, we present textitLLM-based Option-weighted Knowledge Tracing (LOKT), a simple yet effective framework that encodes the interaction histories of example learners in context as textittextual categorical option weights (TCOW). TCOW are semantic labels (e.g., ``inadequate'') assigned to the options selected by learners when answering questions, enhancing the interpretability of LLMs. Experiments on multiple-choice datasets show that LOKT outperforms existing non-LLM and LLM-based KT models in both cold-start and warm-start settings. Moreover, LOKT enables scalable and cost-efficient inference, achieving strong performance even under strict token constraints. Our code is available at hrefhttps://anonymous.4open.science/r/LOKTmodel-3233https://anonymous.4open.science/r/LOKTmodel-3233.