MetaGen Blended RAG: Unlocking Zero-Shot Precision for Specialized Domain Question-Answering
This addresses the challenge of achieving zero-shot precision for specialized domain question-answering in enterprise settings, offering a scalable solution without fine-tuning.
The paper tackles the problem of Retrieval-Augmented Generation (RAG) struggling with domain-specific enterprise datasets due to semantic variability and lack of fine-tuning, achieving 82% retrieval accuracy and 77% RAG accuracy on the biomedical PubMedQA dataset, surpassing prior zero-shot benchmarks.
Retrieval-Augmented Generation (RAG) struggles with domain-specific enterprise datasets, often isolated behind firewalls and rich in complex, specialized terminology unseen by LLMs during pre-training. Semantic variability across domains like medicine, networking, or law hampers RAG's context precision, while fine-tuning solutions are costly, slow, and lack generalization as new data emerges. Achieving zero-shot precision with retrievers without fine-tuning still remains a key challenge. We introduce 'MetaGen Blended RAG', a novel enterprise search approach that enhances semantic retrievers through a metadata generation pipeline and hybrid query indexes using dense and sparse vectors. By leveraging key concepts, topics, and acronyms, our method creates metadata-enriched semantic indexes and boosted hybrid queries, delivering robust, scalable performance without fine-tuning. On the biomedical PubMedQA dataset, MetaGen Blended RAG achieves 82% retrieval accuracy and 77% RAG accuracy, surpassing all prior zero-shot RAG benchmarks and even rivaling fine-tuned models on that dataset, while also excelling on datasets like SQuAD and NQ. This approach redefines enterprise search using a new approach to building semantic retrievers with unmatched generalization across specialized domains.