Retrieval-Augmented Generation (RAG) is essential for integrating external
knowledge into Large Language Model (LLM) outputs. While the literature on RAG
is growing, it primarily focuses on systematic reviews and comparisons of new
state-of-the-art (SoTA) techniques against their predecessors, with a gap in
extensive experimental comparisons. This study begins to address this gap by
assessing various RAG methods' impacts on retrieval precision and answer
similarity. We found that Hypothetical Document Embedding (HyDE) and LLM
reranking significantly enhance retrieval precision. However, Maximal Marginal
Relevance (MMR) and Cohere rerank did not exhibit notable advantages over a
baseline Naive RAG system, and Multi-query approaches underperformed. Sentence
Window Retrieval emerged as the most effective for retrieval precision, despite
its variable performance on answer similarity. The study confirms the potential
of the Document Summary Index as a competent retrieval approach. All resources
related to this research are publicly accessible for further investigation
through our GitHub repository ARAGOG (this https URL). We
welcome the community to further this exploratory study in RAG systems.

整合外部知识到大型语言模型输出，文献调研主要集中于最新方法与之前方法的比较，缺乏广泛的实验比较。本研究通过评估不同检索增强生成方法对检索精度和答案相似性的影响来填补这一空白。研究发现，Hypothetical Document Embedding (HyDE) 和大型语言模型重排能显著提高检索精度。然而，Maximal Marginal Relevance (MMR) 和 Cohere 重排在基线 Naive RAG 系统上没有明显优势，而 Multi-query 方法表现不佳。句窗检索为最有效的检索精度方法，尽管在答案相似性上表现不稳定。研究证实文件摘要索引作为一种有效的检索方法。欢迎学术界进一步探索 RAG 系统的研究，相关资源可通过我们的 GitHub 资源库 ARAGOG 进行进一步调查。

ARAGOG：高级 RAG 输出评分

ARAGOG: Advanced RAG Output Grading

Efficient Maximum Inner Product Search (MIPS) is an important task that has a
wide applicability in recommendation systems and classification with a large
number of classes. Solutions based on locality-sensitive hashing (LSH) as well
as tree-based solutions have been investigated in the recent literature, to
perform approximate MIPS in sublinear time. In this paper, we compare these to
another extremely simple approach for solving approximate MIPS, based on
variants of the k-means clustering algorithm. Specifically, we propose to train
a spherical k-means, after having reduced the MIPS problem to a Maximum Cosine
Similarity Search (MCSS). Experiments on two standard recommendation system
benchmarks as well as on large vocabulary word embeddings, show that this
simple approach yields much higher speedups, for the same retrieval precision,
than current state-of-the-art hashing-based and tree-based methods. This simple
method also yields more robust retrievals when the query is corrupted by noise.

本文主要探讨了最大内积搜索的效率问题，提出了一种基于 k 均值聚类算法的简单方法，在保证检索准确率的同时显著提高检索速度，并在两个标准推荐系统基准测试和大词汇量词嵌入上进行了实验证明。