Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts
This addresses the problem of limited context length in retrieval-augmented open-domain QA for users of large language models, representing an incremental improvement.
The paper tackles the challenge of covering longer contexts in open-domain question-answering due to model size and resource constraints, proposing a method that uses a small encoder language model to encode contexts with cross-attention, enabling origin models to handle several times longer contexts with minimal increase in computing requirements and showing improved performance across multiple datasets and settings.
In the era of large language models, applying techniques such as Retrieval Augmented Generation can better address Open-Domain Question-Answering problems. Due to constraints including model sizes and computing resources, the length of context is often limited, and it becomes challenging to empower the model to cover overlong contexts while answering questions from open domains. This paper proposes a general and convenient method to covering longer contexts in Open-Domain Question-Answering tasks. It leverages a small encoder language model that effectively encodes contexts, and the encoding applies cross-attention with origin inputs. With our method, the origin language models can cover several times longer contexts while keeping the computing requirements close to the baseline. Our experiments demonstrate that after fine-tuning, there is improved performance across two held-in datasets, four held-out datasets, and also in two In Context Learning settings.