About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Parth Sarthi
- sl:arxiv_num : 2401.18059
- sl:arxiv_published : 2024-01-31T18:30:21Z
- sl:arxiv_summary : Retrieval-augmented language models can better adapt to changes in world
state and incorporate long-tail knowledge. However, most existing methods
retrieve only short contiguous chunks from a retrieval corpus, limiting
holistic understanding of the overall document context. We introduce the novel
approach of recursively embedding, clustering, and summarizing chunks of text,
constructing a tree with differing levels of summarization from the bottom up.
At inference time, our RAPTOR model retrieves from this tree, integrating
information across lengthy documents at different levels of abstraction.
Controlled experiments show that retrieval with recursive summaries offers
significant improvements over traditional retrieval-augmented LMs on several
tasks. On question-answering tasks that involve complex, multi-step reasoning,
we show state-of-the-art results; for example, by coupling RAPTOR retrieval
with the use of GPT-4, we can improve the best performance on the QuALITY
benchmark by 20% in absolute accuracy.@en
- sl:arxiv_title : RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval@en
- sl:arxiv_updated : 2024-01-31T18:30:21Z
- sl:bookmarkOf : https://arxiv.org/abs/2401.18059
- sl:creationDate : 2024-02-03
- sl:creationTime : 2024-02-03T21:36:11Z
Documents with similar tags (experimental)
Preferences...