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

Jongwoo Kim, SeongYeub Chu, Bryan Wong, Mun Yong Yi


Abstract
Large Language Models (LLMs) have recently emerged as promising tools for knowledge tracing due to their strong reasoning and generalization abilities. While recent LLM-based KT methods have introduced new prompt formats, they struggle to reflect the histories of example learners within a single prompt during in-context learning (ICL), leading to limited scalability and high computational cost under token constraints. In this work, we present LLM-based Option weighted Knowledge Tracing (LOKT), a simple yet effective LLM-based knowledge tracing framework that encodes the interaction histories of example learners in context as textual categorical option weights (TCOW). These are semantic labels (e.g., “inadequate”) assigned to the options selected by learners when answering questions helping understand LLM. Experiments on multiple-choice datasets show that LOKT outperforms existing LLM-based KT models in both warm-start and few-shot settings. Moreover, LOKT enables scalable and cost-efficient inference, performing strongly even under strict token constraints. Our code is available at https://anonymous.4open.science/r/LOKT_model-3233
Anthology ID:
2025.findings-emnlp.874
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16114–16128
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.874/
DOI:
Bibkey:
Cite (ACL):
Jongwoo Kim, SeongYeub Chu, Bryan Wong, and Mun Yong Yi. 2025. Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 16114–16128, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing (Kim et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.874.pdf
Checklist:
 2025.findings-emnlp.874.checklist.pdf