Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2408.08805 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911991474421760 |
|---|---|
| author | Lopo, Joanito Agili Prasasti, Marina Indah Permatasari, Alma |
| author_facet | Lopo, Joanito Agili Prasasti, Marina Indah Permatasari, Alma |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08805 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems Lopo, Joanito Agili Prasasti, Marina Indah Permatasari, Alma Computation and Language Artificial Intelligence 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. |
| title | CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2408.08805 |