How retriever redundancy and diversity impact RAG effectiveness

In RAG, while the retriever typically ranks documents by their individual relevance to the query, the generator instead produces an answer based on the retrieved documents as a whole. This paper investigates how redundancy and diversity from the retrieved document set impact the generator in terms of answer correctness. Previous work has provided a mix of findings: some showing that redundancy improves generation by reinforcing relevant information, others that LLM-based paraphrasing of the same content may be beneficial. Many of these studies did not control for confounding factors like whether the documents contained the exact answer or not, and if parametric knowledge plays a role. We conduct a carefully controlled experiment investigating three key scenarios of retrieved document sets: 1) Duplicate (exact copies of the same document), 2) Paraphrased (LLM rephrased versions of one document) and 3) Diverse (documents from different genres each containing relevant information in different forms). We control for which documents contain the answer in exact match or rephrased form. Evaluation is done with FictionalQA, a synthetic, fictional question-answer dataset that ensures the LLM generator prior knowledge cannot answer the question; the answer must come from retrieved documents. We show that duplicate redundancy and LLM paraphrasing does not significantly improve answer correctness. However, providing diverse documents is highly beneficial, improving answer correctness by 17%-47%. We further show this improvement is driven by diverse forms of document genre (news, blogs, etc.) alone and not a consequence of more relevant answer being available to generator. Our findings help to direct more attention to how new retrieval methods might improve RAG by catering to the generator preference for diversity in retrieval results.

On the impact of retrieved content representations in RAG Pipelines

Retrieval-Augmented Generation (RAG) supplements a language model's input with retrieved documents, yet most RAG pipelines inherit retrieval components designed for human readers. How retrieved content should be represented when the consumer is a large language model (LLM) rather than a human is less well understood. Recent work has proposed transformations of retrieved content and identified properties that affect generation, but each examines a single transformation or property in isolation, leaving open which features of a document's representation matter most. We address this with a controlled comparison: holding retrieval fixed, we vary only the representation of retrieved documents, comparing an original baseline against thirteen transformations spanning selection, summarisation, and reformulation, in query-dependent and query-independent variants. Across these fourteen representations we measure question-answering accuracy for four generators, and for each representation we also measure answer retention: whether a known answer-bearing document still supports its answer after transformation. We find that answer retention is the primary determinant of generator accuracy; notably, when retention is high, a representation's wording, structure, length, and query-dependence have limited effect. This suggests that accuracy gains attributed to specific mechanisms in prior work may be partly explained by how well those mechanisms preserve answer-bearing content, an attribution that cannot be settled without controlling for retention.