CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems
This work addresses the need for efficient and accurate AI in educational settings, though it is incremental as it builds on existing dual-encoder and language model techniques.
The paper tackles the problem of improving response relevance in educational dialogue systems by introducing CIKMar, a dual-encoder approach using BERT and SBERT with the Gemma model, achieving a recall and F1-score of 0.70 in evaluation.
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.