4arXiv cs.CL (Computation and Language)·
grapheme-kit: Open-source Python library for grapheme-level NLP metrics in multilingual settings
Researchers introduce grapheme-kit, an open-source Python library that extends lexical distance, similarity, and evaluation metrics to operate on Unicode grapheme clusters rather than raw code points. The library targets writing systems where a single grapheme spans multiple code points, with specific improvements for Tamil and Sinhala scripts. An OCR case study demonstrates that grapheme-level metrics yield more faithful evaluation of complex scripts than code-point-level metrics.
Related guides (1)
Related events (8)
CKTN: First multilingual corpus and benchmark for Vietnamese ethnic minority languages Cham, Khmer, and Tay-Nung
Researchers introduce CKTN, the first NLP corpus and benchmark for three underrepresented Vietnamese ethnic minority languages (Cham, Khmer, Tay-Nung), comprising 44,367 documents and 24M subword tokens across pretraining, classification, and retrieval tasks. The paper demonstrates that standard multilingual encoders severely fragment these languages and that common adaptation metrics (language-modeling loss, lexical-overlap retrieval) can be misleading proxies for semantic generalization. The authors propose a script-aware adaptation recipe combining vocabulary augmentation with calibrated replaced-token pretraining, achieving substantially reduced fragmentation and best-in-class classification performance. The work highlights systematic gaps in multilingual NLP coverage and evaluation methodology for low-resource, script-diverse languages.
Graphify: open-source tool to convert codebases into queryable knowledge graphs for AI coding assistants
Graphify is a Python library that converts arbitrary code folders, SQL schemas, scripts, docs, and media into a queryable knowledge graph, designed to serve as a skill or context layer for AI coding assistants including Claude Code, Codex, Cursor, and Gemini CLI. The project has accumulated 72,438 GitHub stars with 504 added today, indicating strong community traction. It targets the problem of giving AI coding agents unified, structured access to heterogeneous project artifacts across code, schema, and infrastructure.
CircuitKIT: unified toolkit for mechanistic interpretability circuit analysis
CircuitKIT is a new source-available Python library that integrates circuit discovery, evaluation, and intervention into a single typed, serializable workflow for mechanistic interpretability research. The library addresses fragmentation in the current ecosystem, where researchers must stitch together separate implementations for discovery algorithms, diagnostics, and downstream applications like pruning, editing, and steering. It includes declarative interfaces for mapping structured data into discovery tasks and is released by Lexsi Labs on GitHub.
LangMAP: Language-adaptive tokenization from a shared vocabulary without language identification at inference
LangMAP (Language-adaptive Maximum a Posteriori Tokenization) extends the UnigramLM algorithm to produce language-specific tokenizations from a single shared vocabulary, eliminating the need to retrain models or swap vocabularies for multilingual settings. A key property is that language labels are only required at training time; inference proceeds without language identification. Evaluated across 14 tokenizers, 9 natural languages, and 9 programming languages, LangMAP improves morphological boundary alignment and AST-leaf alignment for all coding languages tested. Fine-tuning results are mixed: consistent gains on grammatical acceptability (MultiBLiMP) but less consistent on knowledge tasks (Global-PIQA, Belebele).
Graphify: open-source tool turns codebases into queryable knowledge graphs for AI coding assistants
Graphify is an open-source Python library that converts arbitrary code folders, SQL schemas, scripts, docs, and media into a queryable knowledge graph, designed as a skill layer for AI coding assistants including Claude Code, Cursor, and Gemini CLI. The project has accumulated over 80,000 GitHub stars with strong daily momentum (+885 today), suggesting significant community adoption. It targets the problem of giving AI coding agents structured, cross-artifact context across app code, database schemas, and infrastructure simultaneously.
Graph-based clustering recovers Zipfian distributions in unsupervised term discovery
A new arXiv preprint argues that K-means and other centre-based clustering methods produce artificially uniform lexicon distributions in unsupervised speech term discovery, due to their bias toward spherical clusters. The authors propose graph-based clustering using the Leiden algorithm as a bottom-up alternative, demonstrating it substantially outperforms K-means, GMM, and BIRCH on word- and syllable-level lexicon discovery across three languages while producing more Zipf-like distributions. The work challenges the dominance of centre-based methods in this subfield of unsupervised speech processing.
Urdu Katib Handwritten Dataset: Historical Urdu HTR benchmark with CRNN baseline evaluation
Researchers introduce the Urdu Katib Handwritten Dataset (UKHD), the first offline Urdu handwritten text lines dataset drawn from historical Katib (scribe) materials in the Nastalique calligraphic style. The paper evaluates several CRNN-based hybrid architectures for Urdu Handwritten Text Recognition, finding that a CNN-BGRU-CTC model achieves the best character and word error rates. The work addresses a recognized gap in cursive-script HTR research caused by the scarcity of benchmark datasets for Urdu.
HULAT2 multi-agent LangGraph system for Spanish Easy-to-Read text simplification at MER-TRANS 2026
Researchers from HULAT2-UC3M describe their submission to the MER-TRANS 2026 shared task on multilingual Easy-to-Read translation, using a LangGraph-based multi-agent workflow combining Gemini 2.5 Flash and RigoChat-7B-v2. The best run (RUN1) achieved a SARI score of 44.05 using Event-Condition-Action routing and internal quality signals, outperforming a LoRA-adapted generate-evaluate-regenerate baseline. Results show signal-guided multi-agent routing outperforms linear regeneration, while adding lexical support did not automatically improve reference-based scores.