arXiv:2609.37755v1 Announce Type: new Abstract: Purpose: Most Greek papyri remain unpublished and undigitised; a handwritten text recognition (HTR) pipeline that transcribes them automatically would...
Wieszcz‑XIX is a 6.75‑billion‑token corpus of Polish texts from 1800‑1918, comprising 3.1 billion words across 294,369 documents, assembled from Wolne Lektury and the Internet Archive. The pipeline filters, deduplicates, audits for post‑1918 leakage, and splits at the document level, yielding a training set with only 0.04–0.38 % post‑1918 residue. From this corpus the authors train decoder‑only language models ranging from 47 M to 349 M parameters, demonstrating that larger models better preserve period spelling and exhibit temporal boundedness compared to modern Polish baselines.
arXiv:2608. 06305v1 Announce Type: new Abstract: Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query.
The paper audits a 366‑day autobiographical book generated by a large language model (LLM) against an independent verification corpus. Using a four‑level rubric, 354 of the 366 days (96.7%) failed verification, with only 12 days containing corroborated scenes and 19 days containing actively contradicted claims. Regenerating the same days with current models yielded 100% verification failure, while grounding the generation in the subject’s own corpus improved the rate to 83.3% but still left substantial residual failure.
The paper introduces a lightweight CPU-based extension to GROBID that uses layout-guided masking to identify figure, table, and paratext regions in scientific PDFs. By routing tokens to specialized GROBID models or discarding them, the method improves structural accuracy on PMC corpora and enhances figure caption recovery. It also achieves competitive table detection and body‑text precision compared to vision‑based GPU parsers while operating entirely on CPU and costing significantly less.
AraMS-28k is the largest publicly released line‑level dataset of genuine historical Arabic manuscripts, containing 14 books, 3,043 pages, and 28,600 annotated text lines (27,971 main‑text and 629 margin). The dataset spans three script traditions—Naskh, Ruq'ah, and Maghrebi—and includes a lithographed printed edition for format diversity. Each line is labeled as main‑text or margin, with margin lines that have a clear attachment point annotated with an insertion anchor to recover the manuscript’s true non‑linear reading order; both fully vocalized and diacritic‑normalized transcriptions are provided, and the data was produced via the RefLAM pipeline combining OCR, clean transcriptions, and human review. "whyItMatters":"The dataset’s comprehensive line‑level annotations, including reading‑order anchors and dual transcription formats, enable reproducible research on Arabic manuscript recognition, layout analysis, and reading‑order recovery under a CC BY‑NC‑SA 4.0 license."
arXiv:2609.18154v1 Announce Type: cross Abstract: We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite th...
The paper investigates whether language models can identify sentences from their training data by using exact duplication counts from publicly released corpora for two model families, OLMo‑2 and Pythia. It finds that for typical duplication levels, models show only a weak trace of exposure, with a rank correlation near –0.08, and that strong signals only appear when a sentence appears roughly a thousand times, at which point fame rather than memory dominates. The study also demonstrates that common membership tests can be misleading, as changing a single word does not alter the model’s preference, and that controlling for register can significantly improve detector performance.
arXiv:2607. 29539v1 Announce Type: cross Abstract: Standard AI-text detection benchmarks compare human-written text against text generated directly by large language models (LLMs).
arXiv:2608. 19385v1 Announce Type: new Abstract: Historical Arabic manuscript transcription is not only a recognition problem.
arXiv:2609.38021v1 Announce Type: cross Abstract: We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, cove...
The paper reports on a deployed multi‑agent tender‑response system that uses an open‑weights language model under sovereignty constraints. In a blind comparison, the system’s answers were judged at least as good as human‑written bids in 40 of 55 sections, with only a few gaps attributable to missing knowledge rather than writing quality. The study also demonstrates an asymmetry in conditioning: while structural markup improves reading tasks, converting instruction material from prose to nested XML degrades answer quality, and naming forbidden constructions concentrates defects.