S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA

TL;DR

S2G-RAG introduces an iterative retrieval-augmented QA framework with explicit gap-judging to improve multi-hop reasoning and robustness by controlling retrieval based on evidence sufficiency.

Contribution

The paper proposes S2G-RAG, a novel framework with a structured gap-judging component that guides multi-turn retrieval and enhances QA performance without retraining or modifying search engines.

Findings

Improves multi-hop QA accuracy on TriviaQA, HotpotQA, and 2WikiMultiHopQA.

Enhances robustness of retrieval-augmented QA under multi-turn retrieval.

Can be integrated into existing RAG pipelines as a lightweight component.

Abstract

Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterative pipelines must control what to retrieve next and when the available evidence is adequate. In practice, systems may answer from incomplete evidence chains, or they may accumulate redundant or distractor-heavy text that interferes with later retrieval and reasoning. We propose S2G-RAG (Structured Sufficiency and Gap-judging RAG), an iterative framework with an explicit controller, S2G-Judge. At each turn, S2G-Judge predicts whether the current evidence memory supports answering and, if not, outputs structured gap items that describe the missing information. These gap items are then mapped into the next retrieval query, producing stable multi-turn retrieval trajectories. To reduce noise accumulation, S2G-RAG maintains a sentence-level Evidence Context by extracting a compact set of relevant sentences from retrieved documents. Experiments on TriviaQA, HotpotQA, and 2WikiMultiHopQA show that S2G-RAG improves multi-hop QA performance and robustness under multi-turn retrieval. Furthermore, S2G-RAG can be integrated into existing RAG pipelines as a lightweight component, without modifying the search engine or retraining the generator.