Enhancing Retrieval in QA Systems with Derived Feature Association

TL;DR

This paper introduces RAIDD, an extension to RAG systems that uses LLM-derived features like summaries and questions to improve retrieval accuracy in long-context QA tasks.

Contribution

The paper proposes RAIDD, a novel retrieval method that incorporates inferred features from documents to enhance retrieval relevance in QA systems.

Findings

RAIDD outperforms traditional RAG in long-context QA tasks.

Inferred features improve retrieval relevance.

Enhanced retrieval leads to better answer accuracy.

Abstract

Retrieval augmented generation (RAG) has become the standard in long context question answering (QA) systems. However, typical implementations of RAG rely on a rather naive retrieval mechanism, in which texts whose embeddings are most similar to that of the query are deemed most relevant. This has consequences in subjective QA tasks, where the most relevant text may not directly contain the answer. In this work, we propose a novel extension to RAG systems, which we call Retrieval from AI Derived Documents (RAIDD). RAIDD leverages the full power of the LLM in the retrieval process by deriving inferred features, such as summaries and example questions, from the documents at ingest. We demonstrate that this approach significantly improves the performance of RAG systems on long-context QA tasks.