论文标题
改善开放域问题检索增强发电（RAG）模型的域改编
Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering
论文作者
论文摘要
检索增强发电（RAG）是开放域问题答案（ODQA）的最新进步。 RAG仅通过基于Wikipedia的外部知识库进行了培训和探索，并且没有在其他专业领域（例如医疗保健和新闻）中进行优化。在本文中，我们评估了RAG的猎犬和发电机组件的联合培训对ODQA域适应任务的影响。我们建议\ textIt {rag-end2end}（抹布的扩展），可以通过在培训期间更新外部知识库的所有组件来适应特定领域的知识库。此外，我们引入了一个辅助训练信号，以注入更多特定领域的知识。这个辅助信号迫使\ textit {rag-end2end}通过从外部知识库中访问相关信息来重建给定句子。我们的新颖贡献与抹布不同，rag-end2end对QA任务和域名适应的猎犬和发电机进行了联合培训。我们使用来自三个领域的数据集评估了我们的方法：COVID-19，新闻和对话，并与原始的RAG模型相比实现了显着的性能改进。我们的工作已经通过Huggingface Transformers库开源，证明了我们工作的信誉和技术一致性。
Retrieval Augment Generation (RAG) is a recent advancement in Open-Domain Question Answering (ODQA). RAG has only been trained and explored with a Wikipedia-based external knowledge base and is not optimized for use in other specialized domains such as healthcare and news. In this paper, we evaluate the impact of joint training of the retriever and generator components of RAG for the task of domain adaptation in ODQA. We propose \textit{RAG-end2end}, an extension to RAG, that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training. In addition, we introduce an auxiliary training signal to inject more domain-specific knowledge. This auxiliary signal forces \textit{RAG-end2end} to reconstruct a given sentence by accessing the relevant information from the external knowledge base. Our novel contribution is unlike RAG, RAG-end2end does joint training of the retriever and generator for the end QA task and domain adaptation. We evaluate our approach with datasets from three domains: COVID-19, News, and Conversations, and achieve significant performance improvements compared to the original RAG model. Our work has been open-sourced through the Huggingface Transformers library, attesting to our work's credibility and technical consistency.
