Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low. Retrieval-augmented models commonly rely on a semantic retrieval mechanism based on the similarity between dense representations of the query chunk and potential neighbors. In this paper, we study the state-of-the-art Retro model and observe that its performance gain is better explained by surface-level similarities, such as token overlap. Inspired by this, we replace the semantic retrieval in Retro with a surface-level method based on BM25, obtaining a significant reduction in perplexity. As full BM25 retrieval can be computationally costly for large datasets, we also apply it in a re-ranking scenario, gaining part of the perplexity reduction with minimal computational overhead.

翻译：研究表明，为语言模型增加检索机制能够在保持参数数量较少的同时显著提升其性能。检索增强模型通常依赖于基于查询块与潜在邻居的密集表示相似性的语义检索机制。本文研究了最先进的Retro模型，并观察到其性能提升更优地由表面层面的相似性（如词元重叠）解释。受此启发，我们将在Retro中的语义检索替换为基于BM25的表面层面方法，从而显著降低了困惑度。由于针对大规模数据集进行完整BM25检索计算成本较高，我们还在重排序场景中应用了该方法，以最小计算开销获得了部分困惑度降低。