Summary of Cikmar: a Dual-encoder Approach to Prompt-based Reranking in Educational Dialogue Systems, by Joanito Agili Lopo and Marina Indah Prasasti and Alma Permatasari
CIKMar: A Dual-Encoder Approach to Prompt-Based Reranking in Educational Dialogue Systems
by Joanito Agili Lopo, Marina Indah Prasasti, Alma Permatasari
First submitted to arxiv on: 16 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This study introduces CIKMar, an efficient approach to educational dialogue systems powered by the Gemma Language model, leveraging a Dual-Encoder ranking system that incorporates both BERT and SBERT models. The approach is designed to deliver highly relevant and accurate responses despite a smaller language model size. Evaluation reveals a robust recall and F1-score of 0.70 using BERTScore metrics. However, the study identifies a significant challenge: the Dual-Encoder tends to prioritize theoretical responses over practical ones. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research creates a new way for AI systems to help with educational conversations. The system uses a special model called Gemma and combines it with two other models (BERT and SBERT) to make smart decisions. It works really well, even when the language model is smaller than usual. The tests show that this approach can get 70% of answers correct using a specific way to measure accuracy. However, there’s a problem: the system tends to focus on theoretical answers instead of practical ones. |
Keywords
» Artificial intelligence » Bert » Encoder » F1 score » Language model » Recall
