# RefLAM: A Reference-Grounded Line Annotation Pipeline for Historical Arabic Manuscripts

arXiv: https://arxiv.org/abs/2608.25140 · HTML: https://mlsanity.com/paper/2608.25140/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 4 of 4)

- [Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition](https://mlsanity.com/paper/2406.09630/) (2024)
- [HATFormer: Historic Handwritten Arabic Text Recognition with Transformers](https://mlsanity.com/paper/2410.02179/) (2024)
- [Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition](https://mlsanity.com/paper/2410.13305/) (2024)
- [Digital Editions as Distant Supervision for Layout Analysis of Printed Books](https://mlsanity.com/paper/2112.12703/) (2021)

## Built on by (most cited first, 1 of 1)

- [AraMS-28k: The Largest Publicly Released Line-Level Dataset of Historical Arabic Manuscripts with Margin and Insertion-Anchor Annotations](https://mlsanity.com/paper/2608.26921/) (2026)

## Abstract (arXiv)

Existing approaches to building line-level Arabic handwritten-text-recognition (HTR) training data either rely on fully manual annotation, which does not scale, or on automatic OCR-to-reference alignment methods not yet extended to multi-script, two-zone (main-plus-margin) manuscript layouts with a provable correctness guarantee. We present RefLAM (Reference-grounded Line Annotation for Manuscripts), a pipeline converting manuscript page images and clean transcriptions into validated, line-level ground truth without sacrificing human oversight. RefLAM couples a deep-learning page-segmentation model with a multimodal large language model (MLLM) for structured OCR and a diacritic-agnostic fuzzy alignment engine that grounds each OCR line in a contiguous span of the reference text, with a character-level confidence score in [0,100]. A perfect score is provably equivalent to character-for-character identity of the normalised strings (the Confidence-100 rule), verified with no counterexample across the released corpus. A reviewer can thus trust a perfect score, confirming most lines at a glance rather than retyping them, so annotation becomes triaged, with attention concentrated on uncertain alignments. Across 7 fully page-validated books we measured a 75× throughput gain over manual annotation (3,000 vs. 40 lines/hr); applying the same guarantee to 7 further books, we retained 16,533 confidence-100 main-text lines within one week, excluding sub-100 lines rather than manually correcting them. Using RefLAM, we release AraMS-28k: 14 historical Arabic manuscript books, 3,043 pages, and 27,971 main-text and 629 margin-line annotations with bounding boxes, layout labels, and insertion anchors for 191 margin entries (30.4%). We also finetune Muharaf-pretrained baselines (including HATFormer) on AraMS-28k and report CER results confirming its practical utility for downstream HTR training.