BIPED: Pedagogically Informed Tutoring System for ESL Education

TL;DR

This paper introduces BIPED, a dataset and framework for developing pedagogically informed conversational tutoring systems for ESL learners, leveraging GPT-4 and SOLAR-KO to enhance teaching of complex language concepts.

Contribution

The paper creates a novel bilingual pedagogically annotated dataset and proposes a two-step framework for training conversational tutors with diverse pedagogical strategies.

Findings

Models replicate human teaching styles

Models employ diverse pedagogical strategies

Models effectively handle complex language concepts

Abstract

Large Language Models (LLMs) have a great potential to serve as readily available and cost-efficient Conversational Intelligent Tutoring Systems (CITS) for teaching L2 learners of English. Existing CITS, however, are designed to teach only simple concepts or lack the pedagogical depth necessary to address diverse learning strategies. To develop a more pedagogically informed CITS capable of teaching complex concepts, we construct a BIlingual PEDagogically-informed Tutoring Dataset (BIPED) of one-on-one, human-to-human English tutoring interactions. Through post-hoc analysis of the tutoring interactions, we come up with a lexicon of dialogue acts (34 tutor acts and 9 student acts), which we use to further annotate the collected dataset. Based on a two-step framework of first predicting the appropriate tutor act then generating the corresponding response, we implemented two CITS models using GPT-4 and SOLAR-KO, respectively. We experimentally demonstrate that the implemented models not only replicate the style of human teachers but also employ diverse and contextually appropriate pedagogical strategies.