DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models

Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what to retrieve during the text generation process of Large Language Models (LLMs). There are two key elements of this paradigm: identifying the optimal moment to activate the retrieval module (deciding when to retrieve) and crafting the appropriate query once retrieval is triggered (determining what to retrieve). However, current dynamic RAG methods fall short in both aspects. Firstly, the strategies for deciding when to retrieve often rely on static rules. Moreover, the strategies for deciding what to retrieve typically limit themselves to the LLM’s most recent sentence or the last few tokens, while the LLM’s information needs may span across the entire context. To overcome these limitations, we introduce a new framework, DRAGIN, i.e., Dynamic Retrieval Augmented Generation based on the Information Needs of LLMs. Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM’s information needs during the text generation process. We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets.

Introduction. In recent years, large language models (LLMs) have made significant advancements across various natural language processing (NLP) tasks, quickly becoming a critical element in numerous AI applications (Brown et al., 2020; Chowdhery et al., 2022; Touvron et al., 2023a; Scao et al., 2022; Zhang et al., 2022). Despite their impressive capabilities, these models often produce text that seems coherent and plausible but factually incorrect, a problem commonly known as hallucination (Maynez et al., 2020; Zhou et al., 2020; Liu et al., 2021; Ji et al., 2023; Su et al., 2024). To mitigate this issue, Retrieval-Augmented Generation (RAG) has emerged as a prominent solution. RAG enhances LLMs by retrieving and incorporating relevant information from external databases into the LLMs’ inputs. It has demonstrated superior effectiveness across numerous NLP challenges (Khandelwal et al., 2019; Borgeaud et al., 2022; Lewis et al., 2020; Guu et al., 2020; Izacard and Grave, 2020; Jiang et al., 2022; Shi et al., 2023).

Discussion / Conclusion. In this work, we propose DRAGIN, a dynamic RAG framework tailored to address the real-time information needs of LLMs during text generation. By integrating RIND for timely retrieval activation and QFS for precise query formulation, DRAGIN significantly outperforms existing dynamic RAG methods across various knowledge-intensive bench-