HackerPapers

arXiv:2401.18059cs.CL

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Parth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna, Anna Goldie, Christopher D. Manning

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.

arXiv comments
Journal reference
DOI
Subjects
cs.CLComputation and Language cs.LGMachine Learning

On Hacker News

Linked by 9 identifiable commenters in 9 comments across 7 threads, from Mar 2024 to Sep 2024.

Comments linking this paper, per year.

Discussed in comments7 threads

  1. Contextual Retrieval 2 comments

    • HyDE: Hypothetical Document Embeddings [1] RAGAS: RAG Assessment [2] RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval [3] Self-RAG: Self-Reflective Retrieval-Augmented Generation [4] Agentic RAG: Agentic Retrieval-Augmented Generation [5] GraphRAG: Graph…

      williamcottonView on HNParent context

    • These are all "techniques" on top of the foundations of RAG. It's similar to "Chain of Thought" in prompt engineering. You have an underlying technology, and then come up with techniques/frameworks on top. What MVC was for Web dev +15 years ago. RAPTOR for example is a technique…

      santiagobasultoView on HNParent context

  2. Ask HN: RAG and unstructured data from several docs 1 comment

    • Tagging each paragraph is not a good approach. Instead, using LLM to generate a summary based on the clustering of paragraphs could be a good alternative. That's what RAPTOR(https://arxiv.org/html/2401.18059v1) has suggested. Regarding to reranker, it's a pure dynamic solution…

      newpeakView on HNParent context

  3. Systematically Improving Your RAG 1 comment
  4. RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation 1 comment
  5. Show HN: Out-of-the-box text classification models 1 comment

    • I like this approach it treats the problem like a reranker it would be interesting to byo classifiers you could do the embedding to match the hierarchy approach which is a good idea it seems. Also the code for Raptor came out recently and they are showing gains through a…

      jimmySixDOFView on HNParent context

  6. Raptor: Recursive Abstractive Processing for Tree-Organized Retrieval 1 comment

    • code from the paper https://arxiv.org/abs/2401.18059 It introduces a 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, the model retrieves from…

      homarpView on HNParent context

  7. Pg_vectorize: Vector search and RAG on Postgres 2 comments

    • Sounds a little like this recent paper; "RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval" https://arxiv.org/abs/2401.18059

      reerdnaView on HNParent context

    • That looks like it'd be an adjunct strategy IMO. In most cases you want to have the original source material on tap, it helps with explainability and citations. That being said, it seems that everyone working at the state of the art is thinking about using LLMs to summarize…

      CuriouslyCView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.