DeepAI AI Chat
Log In Sign Up

Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering

by   Shamane Siriwardhana, et al.
University of Southern Queensland

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 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 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.


Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

This paper presents a general approach for open-domain question answerin...

End-to-End QA on COVID-19: Domain Adaptation with Synthetic Training

End-to-end question answering (QA) requires both information retrieval (...

A Two-Stage Approach towards Generalization in Knowledge Base Question Answering

Most existing approaches for Knowledge Base Question Answering (KBQA) fo...

Text Embeddings for Retrieval From a Large Knowledge Base

Text embedding representing natural language documents in a semantic vec...

Variational Open-Domain Question Answering

We introduce the Variational Open-Domain (VOD) framework for end-to-end ...

WikiDoMiner: Wikipedia Domain-specific Miner

We introduce WikiDoMiner, a tool for automatically generating domain-spe...

Joint Matrix-Tensor Factorization for Knowledge Base Inference

While several matrix factorization (MF) and tensor factorization (TF) mo...