DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models
This work improves dynamic RAG for LLMs, offering a more adaptive retrieval method that could enhance applications like question answering, but it appears incremental as it builds on existing RAG paradigms.
The paper tackles the problem of dynamic retrieval augmented generation (RAG) for large language models by addressing limitations in deciding when and what to retrieve, introducing the DRAGIN framework that bases decisions on real-time information needs. It achieves superior performance on all tasks across 4 knowledge-intensive datasets, demonstrating effectiveness.
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 real-time 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 real-time Information Needs of LLMs. Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process. We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets. Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method. We have open-sourced all the code, data, and models in GitHub: https://github.com/oneal2000/DRAGIN/tree/main