Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking

• URL: http://arxiv.org/abs/2609.12674v1
• Date: Fri, 11 Sep 2026 10:17:55 GMT
• Title: Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking
• Abstract summary: We introduce Fixed-Range Chunking (FRC), utilizing dynamic programming to partition documents into chunks.<n>We propose a lightweight dual-boundary matching algorithm for chunk alignment, alongside four distinct training strategies.<n> Experimental results show that FRC-based fine-tuning substantially improves 7B LLMs over direct Doc2Doc fine-tuning.
• Score: 14.63808610447174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advanced large language models (LLMs) with long context windows can substantially reduce input truncation in document-level machine translation (DocMT). However, direct Doc2Doc translation remains prone to n-gram repetition and progressive quality degradation. A common remedy is to segment the document into finer-grained chunks. Nonetheless, conventional rule-based chunking approaches fail to handle the length distribution mismatch between training and inference. To address this, we introduce Fixed-Range Chunking (FRC), utilizing dynamic programming to partition documents into chunks within a predefined length interval. By consistently applying FRC during training and inference, the input documents of any length are mapped to the same length distribution, substantially reducing train-test length mismatch. Centered on FRC, we propose a lightweight dual-boundary matching algorithm for chunk alignment, alongside four distinct training strategies. Experimental results show that FRC-based fine-tuning substantially improves 7B LLMs over direct Doc2Doc fine-tuning and outperforms existing DocMT methods on IWSLT2017. We further construct GlobVDoc, a 10-language test set independent of mainstream DocMT training sources, and show that FRC improves out-of-distribution document translation.

Related papers

• REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling [0.0]
  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.
  arXiv  Detail & Related papers  (2026-08-30T16:50:38Z)
• Scaling Unsupervised Word Alignment to Documents via Structural Constraints [38.797311337915175]
  We introduce CTFAlign, a lightweight, training-free approach for document-level word alignment.<n>We also introduce MDPAlign, a simpler alternative that constrains alignments by position with a main diagonal prior.<n>Averaged over three models, CTFAlign reduces word alignment error rate from 0.412 to 0.326.
  arXiv  Detail & Related papers  (2026-08-21T12:13:21Z)
• Improving Long-Context Retrieval with Multi-Prefix Embedding [64.08968715893504]
  Multi-Prefix Embedding partitions a document into chunks separated by EOS tokens, encodes the full sequence in a single causal forward pass, and extracts one embedding at each prefix boundary.<n>MPE retains cross-chunk context, enables chunk-level MaxSim matching, and trains with only document-level relevance labels.
  arXiv  Detail & Related papers  (2026-06-22T17:31:02Z)
• A Dual-Track Framework for Template-Constrained LaTeX Conversion [1.906311743485569]
  Existing approaches largely depend on either deterministic rule-based converters or pure end-to-end Large Language Model (LLM) generation.<n>We introduce a robust Dual-Track Framework that systematically decouples template formatting from document processing.<n>Our method achieves better structural fidelity, diverse layout, and achieves a higher compilation success rate compared to the previous baselines.
  arXiv  Detail & Related papers  (2026-06-22T09:51:11Z)
• Align-then-Slide: A complete evaluation framework for Ultra-Long Document-Level Machine Translation [26.418216341998953]
  We introduce textittextbfAlign-then-Slide, a complete evaluation framework for ultra-long doc-mt.<n>In the Align stage, we automatically infer sentence-level source-target correspondences and rebuild the target to match the source sentence number.<n>In the n-Chunk Sliding Evaluate stage, we calculate averaged metric scores under 1-, 2-, 3- and 4-chunk for multi-granularity assessment.
  arXiv  Detail & Related papers  (2025-09-04T01:50:20Z)
• M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization? [49.53982792497275]
  We investigate whether Large Vision-Language Models (LVLMs) genuinely comprehend interleaved image-text in the document.<n>Existing document understanding benchmarks often assess LVLMs using question-answer formats.<n>We introduce a novel and challenging Multimodal Document Summarization Benchmark (M-DocSum-Bench)<n>M-DocSum-Bench comprises 500 high-quality arXiv papers, along with interleaved multimodal summaries aligned with human preferences.
  arXiv  Detail & Related papers  (2025-03-27T07:28:32Z)
• 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)
• Contextual Document Embeddings [77.22328616983417]
  We propose two complementary methods for contextualized document embeddings. First, an alternative contrastive learning objective that explicitly incorporates the document neighbors into the intra-batch contextual loss. Second, a new contextual architecture that explicitly encodes neighbor document information into the encoded representation.
  arXiv  Detail & Related papers  (2024-10-03T14:33:34Z)
• In-context Pretraining: Language Modeling Beyond Document Boundaries [137.53145699439898]
  In-Context Pretraining is a new approach where language models are pretrained on a sequence of related documents. We introduce approximate algorithms for finding related documents with efficient nearest neighbor search. We see notable improvements in tasks that require more complex contextual reasoning.
  arXiv  Detail & Related papers  (2023-10-16T17:57:12Z)
• XDoc: Unified Pre-training for Cross-Format Document Understanding [84.63416346227176]
  XDoc is a unified pre-trained model which deals with different document formats in a single model. XDoc achieves comparable or even better performance on a variety of downstream tasks compared with the individual pre-trained models.
  arXiv  Detail & Related papers  (2022-10-06T12:07:18Z)
• ERNIE-DOC: The Retrospective Long-Document Modeling Transformer [24.426571160930635]
  We propose ERNIE-DOC, a document-level language pretraining model based on Recurrence Transformers. Two well-designed techniques, namely the retrospective feed mechanism and the enhanced recurrence mechanism enable ERNIE-DOC with much longer effective context length. Various experiments on both English and Chinese document-level tasks are conducted.
  arXiv  Detail & Related papers  (2020-12-31T16:12:48Z)

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.