用分治k均值优化电信问答检索，提升准确率并降低计算成本
Bisecting K-Means in RAG for Enhancing Question-Answering Tasks Performance in Telecommunications
- 用分治k均值对3GPP文档向量聚类，按语义分组加速检索
- 在phi-2和phi-3小模型上分别达到66.12%和72.13%准确率
- 适合资源受限场景下的电信领域智能问答应用
电信领域的问答任务在文献中仍研究较少，主要因该领域标准更新快、变化频繁。本文提出一种专为电信领域设计的检索增强生成框架，针对由3GPP文档构成的数据集。框架引入分治k均值聚类技术，对嵌入向量按内容组织，提升信息检索效率。通过该聚类方法，系统可预先筛选与用户查询最相似的若干簇，增强召回内容的相关性。为降低推理计算开销，框架采用小型语言模型进行测试，在phi-2模型上实现66.12%准确率，在经微调的phi-3模型上达72.13%，同时显著缩短训练时间。
原文摘要 · Abstract (English)
Question-answering tasks in the telecom domain are still reasonably unexplored in the literature, primarily due to the field's rapid changes and evolving standards. This work presents a novel Retrieval-Augmented Generation framework explicitly designed for the telecommunication domain, focusing on datasets composed of 3GPP documents. The framework introduces the use of the Bisecting K-Means clustering technique to organize the embedding vectors by contents, facilitating more efficient information retrieval. By leveraging this clustering technique, the system pre-selects a subset of clusters that are most similar to the user's query, enhancing the relevance of the retrieved information. Aiming for models with lower computational cost for inference, the framework was tested using Small Language Models, demonstrating improved performance with an accuracy of 66.12% on phi-2 and 72.13% on phi-3 fine-tuned models, and reduced training time.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。