LongRAG is a new retrieval-augmented generation framework that focuses on addressing the workload imbalance between the retriever and the reader in traditional RAG frameworks.
Traditional RAG frameworks typically use short texts as retrieval units, such as paragraphs of around 100 words. This requires the retriever to search through a massive corpus for a 'needle in a haystack' (i.e., the exact short text unit containing the answer).
In contrast, the reader only needs to extract the answer from the retrieved short text units, resulting in a relatively lighter workload.
This imbalance, with a 'heavy' retriever and a 'light' reader, can lead to suboptimal performance.
To alleviate this imbalance, LongRAG introduces the concepts of a 'long retriever' and a 'long reader,' constructing the framework around retrieval units of 4,000 words.
LongRAG is a new retrieval-augmented generation framework that focuses on addressing the workload imbalance between the retriever and the reader in traditional RAG frameworks.
Traditional RAG frameworks typically use short texts as retrieval units, such as paragraphs of around 100 words. This requires the retriever to search through a massive corpus for a 'needle in a haystack' (i.e., the exact short text unit containing the answer).
In contrast, the reader only needs to extract the answer from the retrieved short text units, resulting in a relatively lighter workload.
This imbalance, with a 'heavy' retriever and a 'light' reader, can lead to suboptimal performance.
To alleviate this imbalance, LongRAG introduces the concepts of a 'long retriever' and a 'long reader,' constructing the framework around retrieval units of 4,000 words.