--- title: "RefLAM: A Reference-Grounded Line — Guechaoui 2026" description: "Historical Arabic manuscripts are photographed in large numbers, but few have line-level transcriptions that could train handwritten-text-recognition…" authors: ["Mohamed Guechaoui", "Mohamed Diaa Zellagui", "Souleyman Chaib", "Sahraoui Dhelim"] year: 2026 venue: "arXiv:2608.25140" source: "https://arxiv.org/abs/2608.25140" doi: "10.48550/arxiv.2608.25140" arxiv: "2608.25140" licence: "CC BY-NC-SA 4.0 (arXiv)" licence_url: "http://creativecommons.org/licenses/by-nc-sa/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/guechaoui-2026-reflam-reference-grounded-line-annotation/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/guechaoui-2026-reflam-reference-grounded-line-annotation/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/8/) / RefLAM: A Reference-Grounded Line Annotation Pipeline for Historical Arabic Manuscripts # RefLAM: A Reference-Grounded Line Annotation Pipeline for Historical Arabic Manuscripts **Authors:** [Mohamed Guechaoui](https://md.research.elamur.ai/free/en/authors/mohamed-guechaoui/), [Mohamed Diaa Zellagui](https://md.research.elamur.ai/free/en/authors/mohamed-diaa-zellagui/), [Souleyman Chaib](https://md.research.elamur.ai/free/en/authors/souleyman-chaib/), [Sahraoui Dhelim](https://md.research.elamur.ai/free/en/authors/sahraoui-dhelim/) · **Year:** 2026 · **Venue:** arXiv:2608.25140 · **Licence:** [CC BY-NC-SA 4.0 (arXiv)](http://creativecommons.org/licenses/by-nc-sa/4.0/) **Links:** [Publisher's page](https://arxiv.org/abs/2608.25140) · [PDF](https://arxiv.org/pdf/2608.25140) · [DOI 10.48550/arxiv.2608.25140](https://doi.org/10.48550/arxiv.2608.25140) · [arXiv 2608.25140](https://arxiv.org/abs/2608.25140) · [OpenAlex](https://openalex.org/W7204490102) **Citations:** 0 citations (openalex-snapshot · 2026-10-14) · [1](#cited-by) in our library, of the 140884 papers whose bibliographies we read ## Summary Historical Arabic manuscripts are photographed in large numbers, but few have line-level transcriptions that could train handwritten-text-recognition (HTR) models. Annotating by hand is slow, at about 40 lines per hour. RefLAM speeds this up by combining two existing resources: a multimodal LLM that does zero-shot, layout-tagged OCR of whole pages, and a clean scholarly edition of the same text that is not tied to page images. The pipeline segments lines with a Muharaf-trained Kraken model, runs Gemini OCR, normalises both texts in the same diacritic-insensitive way, finds where each page sits in the book-level reference, and aligns each OCR line to a contiguous reference span with a confidence score from 0 to 100. The authors prove that a score of 100 means the normalised strings are identical. Reviewers can therefore confirm such lines almost instantly and spend their effort on uncertain ones. The result is a 75× throughput gain and the released corpus AraMS-28k. HATFormer and Kraken baselines finetuned on it show the corpus is usable for HTR training. ## Key points - Throughput on 7 fully page-validated books rose from 40 to 3,000 lines/hr (75×). For 7 further books, 16,533 confidence-100 main-text lines were kept within one week, and lower-scoring lines were dropped rather than corrected. - AraMS-28k contains 14 books and 3,043 pages, with 27,971 main-text and 629 margin-line annotations. Of the margin entries, 191 (30.4%) carry insertion anchors. It covers Naskh, Ruq'ah and Maghrebi hands plus one lithographed volume. - The tools are a Kraken segmentation model trained on Muharaf, with polygons converted to boxes for easier correction, and Gemini (gemini-3-flash-preview) driven by a versioned prompt (v2.3). - The normalisation step: - strips harakat, superscript alef and kashida; - unifies alef variants, alef-maqsura and ta-marbuta; - removes non-Arabic symbols. Both raw texts are kept (gt_raw, gemini_raw). - A manual audit found no wrong line among those scoring 100. The main limitation is that roughly 70% of margin lines could not be anchored confidently, and a clean transcription must already exist. ## Interesting ideas - A confidence metric whose top value is formally the same as exact equality turns review from uniform checking into triage, because a perfect score can be trusted without inspection. — For Mova (learn): Silver data from witness parsers could auto-accept only arcs where a provably exact agreement criterion holds, and send everything else to LLM teacher tiers or human checks. - Treating fluent LLM output strictly as a noisy hypothesis, and checking it against a trustworthy but unaligned source, makes the alignment score work as a hallucination detector at no extra cost. — For Mova (learn): LLM teacher annotations (frames, roles, answers) could be scored against an independent reference such as the source sentence tokens or VerbNet constraints, with low-agreement items quarantined instead of trained on. - Applying one canonical normalisation operator identically to both sides before comparison, while storing both raw strings, keeps matching robust without losing information for later tasks. — For Mova (tokens): A documented normaliser for quotes, apostrophes, hyphens and case could feed lemma and token matching, with raw forms retained so that generation and error analysis still see the original text. - The authors released only lines that met the strict guarantee and excluded uncertain ones rather than hand-fixing them, which keeps the released data's precision claim honest. — For Mova (tree): Treebank conversion between UD dialects could ship only sentences whose round-trip conversion reproduces the input exactly, and list the rest separately for repair rules. - Keeping a version history of the LLM prompt, with what each revision fixed, makes the pipeline auditable and reproducible together with cached model responses. — For Mova (learn): Teacher-tier prompts and their cached outputs could be versioned the same way, so every silver label can be traced to the exact prompt that produced it. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) ## Cited by Cited by 1 paper of our library cites it (of the 140884 whose bibliographies we read); each has a page here. - [AraMS-28k: The Largest Publicly Released Line-Level Dataset of Historical Arabic Manuscripts with Margin and Insertion-Anchor Annotations](https://md.research.elamur.ai/free/en/papers/guechaoui-2026-arams-28k-largest-publicly-released/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{guechaoui2026reflam, title = {{RefLAM: A Reference-Grounded Line Annotation Pipeline for Historical Arabic Manuscripts}}, author = {Guechaoui, Mohamed and Zellagui, Mohamed Diaa and Chaib, Souleyman and Dhelim, Sahraoui}, year = {2026}, doi = {10.48550/arxiv.2608.25140}, eprint = {2608.25140}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.2608.25140} } ``` - [← previous Reference-free Evaluation at Inference for NER/NEL over OCRed Historical Texts](https://md.research.elamur.ai/free/en/papers/nguyen-2026-reference-free-evaluation-inference-ner/) - [next → Reformulate and Create, Don't Translate: Creating Natural Prompts for Underserved Languages](https://md.research.elamur.ai/free/en/papers/simonsen-2026-reformulate-create-don-t-translate/) - [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/8/)