Question Decomposition for Retrieval-Augmented Generation

Abstract

Abstract: Grounding large language models (LLMs) in verifiable external sources is a well-established strategy for generating reliable answers. Retrieval-augmented generation (RAG) is one such approach, particularly effective for tasks like question answering: it retrieves passages that are semantically related to the question and then conditions the model on this evidence. However, multi-hop questions, such as"Which company among NVIDIA, Apple, and Google made the biggest profit in 2023?,"challenge RAG because relevant facts are often distributed across multiple documents rather than co-occurring in on

Research Question

What is the accuracy drop of LLM-based answer generation in multi-hop RAG systems when using adversarial query perturbations (e.g., synonym substitution, negation) compared to single-hop queries, evaluated on the BEIR benchmark with dense vs. sparse retrievers?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance