Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts

TL;DR

This paper introduces a method to extend context coverage in open-domain question-answering by using a small encoder to create vectorized contexts, improving performance without significantly increasing computational costs.

Contribution

It presents a novel approach that enables large language models to handle longer contexts efficiently through vectorized encoding and cross-attention, enhancing open-domain QA capabilities.

Findings

Improved performance on multiple datasets after fine-tuning.

Extended context coverage with minimal additional computational requirements.

Effective in in-context learning scenarios.

Abstract

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.