@inproceedings{kim-etal-2025-options,
    title = "Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient {LLM}-Based Knowledge Tracing",
    author = "Kim, Jongwoo  and
      Chu, SeongYeub  and
      Wong, Bryan  and
      Yi, Mun Yong",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.874/",
    doi = "10.18653/v1/2025.findings-emnlp.874",
    pages = "16114--16128",
    ISBN = "979-8-89176-335-7",
    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 \textit{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 \textit{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"
}