Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models

• URL: http://arxiv.org/abs/2409.04701v2
• Date: Wed, 2 Oct 2024 15:07:09 GMT
• Title: Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
• Authors: Michael Günther, Isabelle Mohr, Daniel James Williams, Bo Wang, Han Xiao,
• Abstract summary: We introduce a novel method called late chunking, which leverages long context embedding models to first embed all tokens of the long text. The resulting chunk embeddings capture the full contextual information, leading to superior results across various retrieval tasks.
• Score: 5.330795983408874
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Many use cases require retrieving smaller portions of text, and dense vector-based retrieval systems often perform better with shorter text segments, as the semantics are less likely to be over-compressed in the embeddings. Consequently, practitioners often split text documents into smaller chunks and encode them separately. However, chunk embeddings created in this way can lose contextual information from surrounding chunks, resulting in sub-optimal representations. In this paper, we introduce a novel method called late chunking, which leverages long context embedding models to first embed all tokens of the long text, with chunking applied after the transformer model and just before mean pooling - hence the term late in its naming. The resulting chunk embeddings capture the full contextual information, leading to superior results across various retrieval tasks. The method is generic enough to be applied to a wide range of long-context embedding models and works without additional training. To further increase the effectiveness of late chunking, we propose a dedicated fine-tuning approach for embedding models.

Related papers

• LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models [73.13933847198395]
  We propose a training-free framework for processing long texts, utilizing a divide-and-conquer strategy to achieve comprehensive document understanding. The proposed LLM$times$MapReduce framework splits the entire document into several chunks for LLMs to read and then aggregates the intermediate answers to produce the final output.
  arXiv  Detail & Related papers  (2024-10-12T03:13:44Z)
• A Novel LLM-based Two-stage Summarization Approach for Long Dialogues [9.835499880812646]
  This study proposes a hierarchical framework that segments and condenses information from long documents. The condensation stage utilizes an unsupervised generation model to generate condensed data. The summarization stage fine-tunes the abstractive summarization model on the condensed data to generate the final results.
  arXiv  Detail & Related papers  (2024-10-09T03:42:40Z)
• Extending Context Window of Large Language Models via Semantic Compression [21.35020344956721]
  Large Language Models (LLMs) often impose limitations on the length of the text input to ensure the generation of fluent and relevant responses. We propose a novel semantic compression method that enables generalization to texts 6-8 times longer, without incurring significant computational costs or requiring fine-tuning.
  arXiv  Detail & Related papers  (2023-12-15T07:04:33Z)
• LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts [60.54912319612113]
  Diffusion-based generative models have significantly advanced text-to-image generation but encounter challenges when processing lengthy and intricate text prompts. We present a novel approach leveraging Large Language Models (LLMs) to extract critical components from text prompts. Our evaluation on complex prompts featuring multiple objects demonstrates a substantial improvement in recall compared to baseline diffusion models.
  arXiv  Detail & Related papers  (2023-10-16T17:57:37Z)
• Adapting Language Models to Compress Contexts [71.98287002918941]
  Transformer-based language models (LMs) are powerful and widely-applicable tools, but their usefulness is constrained by a finite context window. We propose to adapt pre-trained LMs into AutoCompressors, which are capable of compressing long contexts into compact summary vectors. We fine-tune OPT and Llama-2 models on sequences of up to 30,720 tokens and show that AutoCompressors can utilize long contexts to improve perplexity.
  arXiv  Detail & Related papers  (2023-05-24T06:42:44Z)
• 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)
• Adapting Pretrained Text-to-Text Models for Long Text Sequences [39.62224414485055]
  We adapt an existing pretrained text-to-text model for long-sequence inputs. We build a long-context model that achieves competitive performance on long-text QA tasks.
  arXiv  Detail & Related papers  (2022-09-21T00:41:07Z)
• HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization [57.798070356553936]
  HETFORMER is a Transformer-based pre-trained model with multi-granularity sparse attentions for extractive summarization. Experiments on both single- and multi-document summarization tasks show that HETFORMER achieves state-of-the-art performance in Rouge F1.
  arXiv  Detail & Related papers  (2021-10-12T22:42:31Z)
• Toward the Understanding of Deep Text Matching Models for Information Retrieval [72.72380690535766]
  This paper aims at testing whether existing deep text matching methods satisfy some fundamental gradients in information retrieval. Specifically, four attributions are used in our study, i.e., term frequency constraint, term discrimination constraint, length normalization constraints, and TF-length constraint. Experimental results on LETOR 4.0 and MS Marco show that all the investigated deep text matching methods satisfy the above constraints with high probabilities in statistics.
  arXiv  Detail & Related papers  (2021-08-16T13:33:15Z)
• Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension [59.80926970481975]
  We study machine reading comprehension (MRC) on long texts. A model takes as inputs a lengthy document and a question and then extracts a text span from the document as an answer. We propose to let a model learn to chunk in a more flexible way via reinforcement learning.
  arXiv  Detail & Related papers  (2020-05-16T18:08:58Z)
• Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching [28.190001111358438]
  We propose a Siamese Multi-depth Transformer-based SMITH for long-form document matching. Our model contains several innovations to adapt self-attention models for longer text input. We will open source a Wikipedia based benchmark dataset, code and a pre-trained checkpoint to accelerate future research on long-form document matching.
  arXiv  Detail & Related papers  (2020-04-26T07:04:08Z)

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.