CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems

TL;DR

CIKMar is a dual-encoder prompt-based reranking method utilizing BERT and SBERT within the Gemma language model to improve response relevance in educational dialogue systems, balancing efficiency and accuracy.

Contribution

Introduces CIKMar, a novel dual-encoder reranking approach that enhances educational dialogue responses using smaller language models like Gemma.

Findings

Achieves 0.70 recall and F1-score with BERTScore metrics.

Dual-Encoder favors theoretical over practical responses.

Demonstrates effectiveness of compact models in educational AI.

Abstract

In this study, we introduce CIKMar, an efficient approach to educational dialogue systems powered by the Gemma Language model. By leveraging a Dual-Encoder ranking system that incorporates both BERT and SBERT model, we have designed CIKMar to deliver highly relevant and accurate responses, even with the constraints of a smaller language model size. Our evaluation reveals that CIKMar achieves a robust recall and F1-score of 0.70 using BERTScore metrics. However, we have identified a significant challenge: the Dual-Encoder tends to prioritize theoretical responses over practical ones. These findings underscore the potential of compact and efficient models like Gemma in democratizing access to advanced educational AI systems, ensuring effective and contextually appropriate responses.