Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy

By Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, Weizhu Chen. Conference on Empirical Methods in Natural Language Processing, 2023

536 citations recorded by the source corpus.

Large language models are powerful text processors and reasoners, but are still subject to limitations including outdated knowledge and hallucinations, which necessitates connecting them to the world. Retrieval-augmented large language models have raised extensive attention for grounding model generation on external knowledge. However, retrievers struggle to capture relevance, especially for queries with complex information needs. Recent work has proposed to improve relevance modeling by having large language models actively involved in retrieval, i.e., to improve retrieval with generation. In this paper, we show that strong performance can be achieved by a method we call Iter-RetGen, which synergizes retrieval and generation in an iterative manner. A model output shows what might be needed to finish a task, and thus provides an informative context for retrieving more relevant knowledge which in turn helps generate a better output in the next iteration. Compared with recent work which interleaves retrieval with generation when producing an output, Iter-RetGen processes all retrieved knowledge as a whole and largely preserves the flexibility in generation without structural constraints. We evaluate Iter-RetGen on multi-hop question answering, fact verification, and commonsense reasoning, and show that it can flexibly leverage parametric knowledge and non-parametric knowledge, and is superior to or competitive with state-of-the-art retrieval-augmented baselines while causing fewer overheads of retrieval and generation. We can further improve performance via generation-augmented retrieval adaptation.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/a1675f47125aa409525c5f759b5e6bcc1c8831aa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Haofen Wang

Citations in the corpus

• Large Language Models for Information Retrieval: A Survey (2023, unknown): “Recent approaches such as REPLUG [168] and Atlas [169] have improved them by leveraging LLMs such as GPTs, T5s, and LLaMAs for response generation.”
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization (2024, background): “…generation-augmented retrieval (GAR, Mao et al., 2020) that facilitates future generation cycles, while our parallel generation of community answers from these summaries is a kind of iterative (Iter-RetGen, Shao et al., 2023) or federated (FeB4RAG, Wang et al., 2024) retrieval-generation strategy.”
• Retrieval-Augmented Generation for Large Language Models: A Survey (2023, methodology): “ITER-RETGEN [Shao et al. , 2023] employs a synergistic approach that leverages “retrieval-enhanced generation” alongside “generation-enhanced re-trieval” for tasks that necessitate the reproduction of specific information.”
• WebThinker: Empowering Large Reasoning Models with Deep Research Capability (2025, unknown): “…existing open-source deep search agents typically employ retrieval-augmented generation (RAG) techniques with predefined workflows [1, 63, 43], which limits LRM’s ability to explore deeper web information and hinders close interaction between LRMs and search engines (Figure 2 (a) & (b)).”
• Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024, unknown): “ITER-RETGEN [219] synergizes retrieval and generation in an iterative manner.”
• A-MEM: Agentic Memory for LLM Agents (2025, unknown): “To enrich each memory note with meaningful context beyond its basic content and timestamp, we leverage an LLM to analyze the interaction and generate these semantic components.”
• A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models (2024, unknown): “In this part, we will briefly review studies with these two types of generators: parameter-accessible (white-box) and parameter-inaccessible (black-box).”
• Min-Cost Flow Routing for Evidence Assembly in Long Multimodal Documents (2026, unknown): “Iterative retrieval alternates evidence acquisition with reasoning (Press et al., 2023; Yao et al., 2023; Trivedi et al., 2023; Jiang et al., 2023; Shao et al., 2023; Asai et al., 2023).”
• RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering (2026, unknown): “IRCoT inter-leaves chain-of-thought reasoning with retrieval queries (Trivedi et al., 2023), and ITER-RetGen alternates between retrieval and generation in the document (Shao et al., 2023).”
• RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation (2025, unknown): “Iterative retrieval-generation approaches (Shao et al., 2023; Guan et al., 2024) leverage historical context to enhance subsequent retrievals.”