对比文档切分方法，发现递归字符切分更保上下文
Exploring Information Retrieval Landscapes: An Investigation of a Novel Evaluation Techniques and Comparative Document Splitting Methods
- 用递归字符切分法比基于词元的切分更能保持上下文连贯性
- 新评估方法生成问答对数据集，提升测试效率和指标可靠性
- 适合关注RAG系统评测与文档处理优化的研究者
检索增强生成（RAG）系统在信息检索中的表现受文档特征显著影响。本研究发现，教科书的结构化、文章的简洁性以及小说的叙事复杂性需采用不同的检索策略。通过对比多种文档切分方法，结果表明递归字符切分法在保持上下文完整性方面优于基于词元的切分法。本文提出一种新型评估技术，利用开源模型生成大规模问答对数据集，模拟真实检索场景，以提高测试效率与评价指标的可靠性。评估采用加权评分机制，包括SequenceMatcher、BLEU、METEOR和BERT Score，用于衡量系统准确性与相关性。该方法为RAG系统的精度评估建立了更精细的标准，未来研究将聚焦于优化分块大小与重叠长度以提升检索准确率与效率。
原文摘要 · Abstract (English)
The performance of Retrieval-Augmented Generation (RAG) systems in information retrieval is significantly influenced by the characteristics of the documents being processed. In this study, the structured nature of textbooks, the conciseness of articles, and the narrative complexity of novels are shown to require distinct retrieval strategies. A comparative evaluation of multiple document-splitting methods reveals that the Recursive Character Splitter outperforms the Token-based Splitter in preserving contextual integrity. A novel evaluation technique is introduced, utilizing an open-source model to generate a comprehensive dataset of question-and-answer pairs, simulating realistic retrieval scenarios to enhance testing efficiency and metric reliability. The evaluation employs weighted scoring metrics, including SequenceMatcher, BLEU, METEOR, and BERT Score, to assess the system's accuracy and relevance. This approach establishes a refined standard for evaluating the precision of RAG systems, with future research focusing on optimizing chunk and overlap sizes to improve retrieval accuracy and efficiency.
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。