Work

BJTU at BEA 2025 Shared Task: Task-Aware Prompt Tuning and Data Augmentation for Evaluating AI Math Tutors

Year: 2025

Type: conference-paper

Abstract: We describe the BJTU submission to the BEA 2025 Shared Task on Evaluating the Pedagogical Ability of AI Tutors, which focuses on assessing AI-generated math tutoring responses across four dimensions: Mistake Identification, Mistake Location, Guidance, and Actionability.Our approach leverages a large language model (LLM) with task-specific prompt tuning and data augmentation techniques, including dialogue shuffling and class balancing.The system achieves strong results across all tracks, ranking first in Mistake Identification and performing competitively in the others.Our findings underscore the potential of prompt-based LLMs for pedagogically-aware response evaluation and offer insights into the design of AI tutors with improved educational feedback.

Source: Workshop on Innovative Use of NLP for Building Educational Applications

DOI: 10.18653/v1/2025.bea-1.82

Authors: Yuming Fan, Chuangchuang Tan, Wenyu Song

Institution: Beijing Jiaotong University

Language: English

Topic: Intelligent Tutoring Systems and Adaptive Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: hybrid

OpenAlex ID: W4412889237