RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

• URL: http://arxiv.org/abs/2401.18059v1
• Date: Wed, 31 Jan 2024 18:30:21 GMT
• Title: RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
• Authors: Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, Christopher D. Manning
• Abstract summary: We introduce the novel approach of 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.
• Score: 26.527911244587134
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Recursive Abstractive Processing for Retrieval in Dynamic Datasets [0.0]
  We propose a new algorithm to efficiently maintain the recursive-abstractive tree structure in dynamic datasets. We also introduce a novel post-retrieval method that applies query-focused abstractive processing to substantially improve context quality. Our method overcomes the limitations of other approaches by functioning as a black-box post-retrieval layer compatible with any retrieval algorithm.
  arXiv  Detail & Related papers  (2024-10-02T16:47:35Z)
• Corrective Retrieval Augmented Generation [36.04062963574603]
  Retrieval-augmented generation (RAG) relies heavily on relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. We propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches.
  arXiv  Detail & Related papers  (2024-01-29T04:36:39Z)
• Enriching Relation Extraction with OpenIE [70.52564277675056]
  Relation extraction (RE) is a sub-discipline of information extraction (IE) In this work, we explore how recent approaches for open information extraction (OpenIE) may help to improve the task of RE. Our experiments over two annotated corpora, KnowledgeNet and FewRel, demonstrate the improved accuracy of our enriched models.
  arXiv  Detail & Related papers  (2022-12-19T11:26:23Z)
• Document-Level Abstractive Summarization [0.0]
  We study how efficient Transformer techniques can be used to improve the automatic summarization of very long texts. We propose a novel retrieval-enhanced approach which reduces the cost of generating a summary of the entire document by processing smaller chunks.
  arXiv  Detail & Related papers  (2022-12-06T14:39:09Z)
• Retrieval Augmentation for Commonsense Reasoning: A Unified Approach [64.63071051375289]
  We propose a unified framework of retrieval-augmented commonsense reasoning (called RACo) Our proposed RACo can significantly outperform other knowledge-enhanced method counterparts.
  arXiv  Detail & Related papers  (2022-10-23T23:49:08Z)
• UnifieR: A Unified Retriever for Large-Scale Retrieval [84.61239936314597]
  Large-scale retrieval is to recall relevant documents from a huge collection given a query. Recent retrieval methods based on pre-trained language models (PLM) can be coarsely categorized into either dense-vector or lexicon-based paradigms. We propose a new learning framework, UnifieR which unifies dense-vector and lexicon-based retrieval in one model with a dual-representing capability.
  arXiv  Detail & Related papers  (2022-05-23T11:01:59Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• Long Document Summarization with Top-down and Bottom-up Inference [113.29319668246407]
  We propose a principled inference framework to improve summarization models on two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets.
  arXiv  Detail & Related papers  (2022-03-15T01:24:51Z)
• RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization [25.434558112121778]
  We propose a novel retrieval enhanced abstractive summarization framework consisting of a dense Retriever and a Summarizer. We validate our method on a wide range of summarization datasets across multiple domains and two backbone models: BERT and BART. Results show that our framework obtains significant improvement by 1.384.66 in ROUGE-1 score when compared with the powerful pre-trained models.
  arXiv  Detail & Related papers  (2021-09-16T12:52:48Z)
• Text Summarization with Latent Queries [60.468323530248945]
  We introduce LaQSum, the first unified text summarization system that learns Latent Queries from documents for abstractive summarization with any existing query forms. Under a deep generative framework, our system jointly optimize a latent query model and a conditional language model, allowing users to plug-and-play queries of any type at test time. Our system robustly outperforms strong comparison systems across summarization benchmarks with different query types, document settings, and target domains.
  arXiv  Detail & Related papers  (2021-05-31T21:14:58Z)
• A Divide-and-Conquer Approach to the Summarization of Long Documents [4.863209463405628]
  We present a novel divide-and-conquer method for the neural summarization of long documents. Our method exploits the discourse structure of the document and uses sentence similarity to split the problem into smaller summarization problems. We demonstrate that this approach paired with different summarization models, including sequence-to-sequence RNNs and Transformers, can lead to improved summarization performance.
  arXiv  Detail & Related papers  (2020-04-13T20:38:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.