Generator-Retriever-Generator Approach for Open-Domain Question Answering
This addresses the problem of generating accurate answers in open-domain QA for users needing reliable information retrieval, though it is incremental as it builds on existing retrieval and generation pipelines.
The paper tackles open-domain question answering by proposing a Generator-Retriever-Generator (GRG) approach that combines document retrieval with large language models, resulting in performance improvements of at least +5.2, +4.2, and +1.6 on TriviaQA, NQ, and WebQ datasets compared to state-of-the-art methods.
Open-domain question answering (QA) tasks usually require the retrieval of relevant information from a large corpus to generate accurate answers. We propose a novel approach called Generator-Retriever-Generator (GRG) that combines document retrieval techniques with a large language model (LLM), by first prompting the model to generate contextual documents based on a given question. In parallel, a dual-encoder network retrieves documents that are relevant to the question from an external corpus. The generated and retrieved documents are then passed to the second LLM, which generates the final answer. By combining document retrieval and LLM generation, our approach addresses the challenges of open-domain QA, such as generating informative and contextually relevant answers. GRG outperforms the state-of-the-art generate-then-read and retrieve-then-read pipelines (GENREAD and RFiD) improving their performance by at least by +5.2, +4.2, and +1.6 on TriviaQA, NQ, and WebQ datasets, respectively. We provide code, datasets, and checkpoints at https://github.com/abdoelsayed2016/GRG.