Retrieval Augmented Generation for Domain-specific Question Answering
This addresses the issue of general large language models lacking domain-specific understanding for applications like finance or customer service, though it appears incremental as it adapts existing methods to a specific domain.
The authors tackled the problem of domain-specific question answering by building a system for Adobe products, proposing a framework to compile a large QA database and develop retrieval-aware fine-tuning of a large language model, which reduces hallucinations and improves generation.
Question answering (QA) has become an important application in the advanced development of large language models. General pre-trained large language models for question-answering are not trained to properly understand the knowledge or terminology for a specific domain, such as finance, healthcare, education, and customer service for a product. To better cater to domain-specific understanding, we build an in-house question-answering system for Adobe products. We propose a novel framework to compile a large question-answer database and develop the approach for retrieval-aware finetuning of a Large Language model. We showcase that fine-tuning the retriever leads to major improvements in the final generation. Our overall approach reduces hallucinations during generation while keeping in context the latest retrieval information for contextual grounding.