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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kim, JongWoo, Chu, SeongYeub, Wong, Bryan, Yi, Mun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910987837243392
author Kim, JongWoo
Chu, SeongYeub
Wong, Bryan
Yi, Mun
author_facet Kim, JongWoo
Chu, SeongYeub
Wong, Bryan
Yi, Mun
contents 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 \textit{LLM-based Option-weighted Knowledge Tracing (LOKT)}, a simple yet effective framework that encodes the interaction histories of example learners in context as \textit{textual 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 \href{https://anonymous.4open.science/r/LOKT_model-3233}{https://anonymous.4open.science/r/LOKT\_model-3233}.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12872
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
Kim, JongWoo
Chu, SeongYeub
Wong, Bryan
Yi, Mun
Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
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 \textit{LLM-based Option-weighted Knowledge Tracing (LOKT)}, a simple yet effective framework that encodes the interaction histories of example learners in context as \textit{textual 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 \href{https://anonymous.4open.science/r/LOKT_model-3233}{https://anonymous.4open.science/r/LOKT\_model-3233}.
title Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracing
topic Computation and Language
Artificial Intelligence
Computers and Society
Machine Learning
url https://arxiv.org/abs/2410.12872