REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling

• URL: http://arxiv.org/abs/2608.29899v2
• Date: Tue, 01 Sep 2026 07:07:54 GMT
• Title: REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling
• Abstract summary: REIGN is a bi-encoder that operates on sequences of contextualised chunk embeddings from a frozen Guidance Network (GN) rather than on raw tokens.<n>We release a synthetic long-document retrieval benchmark for contrastive training and evaluation at long context lengths.<n>A paired significance test puts it on par with models 1.6-4.3x larger on the patent task, and it stays within 0.65 nDCG@10 of a 20x-larger model on LoCo.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models reach 32K tokens only through architectural workarounds or by stretching billion-parameter LLMs. We propose REIGN (Refurbished Embeddings with Integrated Guidance Networks), a contrastively trained bi-encoder that operates on sequences of contextualised chunk embeddings from a frozen Guidance Network (GN) rather than on raw tokens. REIGN targets multi-chunk inputs, primarily for document-to-document retrieval; single-chunk inputs stay with the GN. Decoupling token-level processing from document-level reasoning, and caching the GN embeddings to disk, cuts per-document training cost by roughly four orders of magnitude relative to chunked Transformer fine-tuning. We also release a synthetic long-document retrieval benchmark for contrastive training and evaluation at long context lengths. Across an in-distribution Wikipedia benchmark, the LoCo out-of-distribution suite, and a real-world patent retrieval case study, REIGN matches dense long-context retrievers at smaller parameter budgets in each regime. A paired significance test puts it on par with models 1.6-4.3x larger on the patent task, and it stays within 0.65 nDCG@10 of a 20x-larger model on LoCo.

Related papers

• TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents [50.64307290680222]
  TongGuOCR is a layout-aware and token-augmented multimodal large language model (MLLM) for OCR of Chinese historical documents.<n>TongGuOCR achieves 93.76 AR and reduces NED from 10.43 to 6.15 and RO-ED from 7.53 to 3.49 relative to the best competing score for each metric.
  arXiv  Detail & Related papers  (2026-08-08T04:50:00Z)
• Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets [3.5312864406384485]
  Large language models (LLMs) for code completion and generation may reproduce training examples verbatim and without authorship attribution.<n> Classical fingerprint-based plagiarism detectors based on fingerprinting, such as Winnowing, remain highly effective.<n>We introduce a 300M- parameter encoder tailored for code retrieval, together with a hybrid two-stage provenance-tracking pipeline.
  arXiv  Detail & Related papers  (2026-05-27T14:12:17Z)
• Training-Free Acceleration for Document Parsing Vision-Language Model with Hierarchical Speculative Decoding [102.88996030431662]
  We propose a training-free and highly efficient acceleration method for document parsing tasks.<n>Inspired by speculative decoding, we employ a lightweight document parsing pipeline as a draft model to predict batches of future tokens.<n>We demonstrate the effectiveness of our approach on the general-purpose OmniDocBench.
  arXiv  Detail & Related papers  (2026-02-13T14:22:10Z)
• Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation [6.4453302264198165]
  We present Hierarchical Embedding Fusion (HEF), a two-stage approach to repository representation for code completion.<n>HEF achieves exact-match accuracy comparable to snippet-based retrieval baselines.<n>Compared to graph-based and iterative retrieval systems, HEF reduces median end-to-end latency by 13 to 26 times.
  arXiv  Detail & Related papers  (2026-02-04T14:56:11Z)
• CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning [48.56088080889236]
  We introduce CorpusQA, a new benchmark scaling up to 10 million tokens, generated via a novel data synthesis framework.<n>We show that finetuning on our synthesized data effectively enhances an LLM's general long-context reasoning capabilities.<n>Our findings indicate that memory-augmented agentic architectures offer a more robust alternative.
  arXiv  Detail & Related papers  (2026-01-21T12:52:30Z)
• SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension [77.93156509994994]
  We show how to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.<n>Existing embedding models are not well-equipped to encode such situated context effectively.<n>Our method substantially outperforms state-of-the-art embedding models.
  arXiv  Detail & Related papers  (2025-08-03T23:59:31Z)
• Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing [46.14775667559124]
  layoutRL is an end-to-end reinforcement learning framework that trains models to be explicitly layout-aware.<n>We will publicly release our code and dataset to accelerate progress in robust document understanding.
  arXiv  Detail & Related papers  (2025-06-01T15:19:52Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• Efficient Document Ranking with Learnable Late Interactions [73.41976017860006]
  Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized query and document embeddings. Recently, late-interaction models have been proposed to realize more favorable latency-quality tradeoffs, by using a DE structure followed by a lightweight scorer.
  arXiv  Detail & Related papers  (2024-06-25T22:50:48Z)
• Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT [48.35407228760352]
  Retrieval pipelines perform poorly in domains where documents are long (e.g., 10K tokens or more) and where identifying the relevant document requires synthesizing information across the entire text. We develop long-context retrieval encoders suitable for these domains. We first introduce LoCoV1, a novel 12 task benchmark constructed to measure long-context retrieval where chunking is not possible or not effective. We next present the M2-BERT retrieval encoder, an 80M parameter state-space encoder model built from the Monarch Mixer architecture, capable of scaling to documents up to 32K tokens long.
  arXiv  Detail & Related papers  (2024-02-12T06:43:52Z)
• Binary Embedding-based Retrieval at Tencent [30.44247353560061]
  Large-scale embedding-based retrieval (EBR) is the cornerstone of search-related industrial applications. We propose a binary embedding-based retrieval engine equipped with a recurrent binarization algorithm that enables customized bits per dimension. We successfully employed the introduced BEBR to Tencent products, including Sogou, Tencent Video, QQ World, etc.
  arXiv  Detail & Related papers  (2023-02-17T06:10:02Z)
• Sparse, Dense, and Attentional Representations for Text Retrieval [25.670835450331943]
  Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors. We investigate the capacity of this architecture relative to sparse bag-of-words models and attentional neural networks. We propose a simple neural model that combines the efficiency of dual encoders with some of the expressiveness of more costly attentional architectures.
  arXiv  Detail & Related papers  (2020-05-01T02:21:17Z)

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.