arXiv AI

IHUBERT: Vector-Based Semantic Deduplication and Domain-Balanced Pretraining for Persian Resources

arXiv:2606. 20089v1 Announce Type: cross Abstract: Persian pretrained language models (PLMs) are still limited by the scarcity of large-scale, high-quality pretraining corpora and by insufficient evaluation beyond standard classification and NER tasks.

arXiv Machine Learning

Jun 2

GottBERT: a pure German Language Model

arXiv:2012. 02110v2 Announce Type: replace-cross Abstract: Pre-trained language models have significantly advanced natural language processing (NLP), especially with the introduction of BERT and its optimized version, RoBERTa.

By Raphael Scheible, Johann Frei, Fabian Thomczyk, Henry He, Patric Tippmann, Jochen Knaus, Victor Jaravine, Frank Kramer, Martin Boeker

llms nlp

arXiv AI

Jul 28

CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data

arXiv:2607. 22662v1 Announce Type: new Abstract: Open-web corpora curated via highly selective filters, such as FineWeb-Edu and DCLM, constitute the core of LLM pretraining data and have significantly advanced LLM performance.

By Peiguang Li, Yongwei Zhou, Juncheng Diao, Yuchun Fan, Jian Yang, Jianxiao Yang, Zhongda Su, Shuguang Jiao, Xiao Wei, Zhiye Zou, Gan Dong, Zhizhao Zeng, Rongxiang Weng, Jingang Wang, Xunliang Cai

llms efficiency benchmarks

arXiv AI

Jul 1

Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian

arXiv:2606. 31718v1 Announce Type: cross Abstract: Relation extraction (RE) for low-resource languages is typically constrained by the lack of annotated corpora.

By Dragos-Mitrut Vasile, Elena-Simona Apostol, Stefan-Adrian Toma, Adrian Paschke, Ciprian-Octavian Truica

llms fine-tuning benchmarks

arXiv Machine Learning

Aug 11

Embedding Initialization for Unseen Low-resource Languages in Multilingual NMT: A Case Study on Limbum-English Translation

arXiv:2608. 07629v1 Announce Type: cross Abstract: Multilingual neural machine translation models such as NLLB-200 cover 200 languages but leave thousands unsupported, including most Grassfields Bantu languages of Cameroon.

By Samiratu Ntohsi, Neza David Tuyishimire, Anesu Kafesu, Marvin Ogore, Samuel Oluwajunwonlo Babalola, Oche Ankeli

llms rag nlp fine-tuning

arXiv Machine Learning

Aug 7

Sparse Mutual Information Graph Averaging for Improving Random Indexing Embeddings

arXiv:2608. 05724v1 Announce Type: cross Abstract: Sparse word embedding pipelines can avoid dense co-occurrence matrix materialization, dense factorization, and gradient training while still relying on sparse global corpus statistics.

By Sriram Loganathan, Gokul Anand, Aung Bo Bo, Yourui Shao, William B. Andreopoulos

rag nlp efficiency

Hugging Face Trending Papers

Jul 1

MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages

Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synthetic parallel corpus with approximately 4.

llms benchmarks

arXiv AI

Jun 12

SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation

arXiv:2606. 13647v1 Announce Type: cross Abstract: We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types -- nearly 4$\times$ the depth of existing multilingual benchmark coverage for Slovak.

By Marek \v{S}uppa, Andrej Ridzik, Daniel Hl\'adek, Nat\'alia K\v{n}a\v{z}ekov\'a, Vikt\'oria Ondrejov\'a

rag fine-tuning benchmarks

arXiv AI

Jul 17

In-Place Tokenizer Expansion for Pre-trained LLMs

arXiv:2607. 15232v1 Announce Type: cross Abstract: A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time.

By Jimmy T. H. Smith, Tarek Dakhran, Alberto Cabrera, Simon S. Lee, Paul Pak, Aditya Tadimeti, Tim Seyde, Maxime Labonne, Alexander Amini, Mathias Lechner

llms rag nlp

arXiv Machine Learning

1d ago

L3Cube-IndicQuest v2: A Large-Scale Multilingual Benchmark for Evaluating Factual Knowledge of Large Language Models Across Indic Languages

arXiv:2608. 15535v1 Announce Type: cross Abstract: We present L3Cube-IndicQuest v2, a large-scale gold-standard multilingual question-answering benchmark for evaluating the India-specific factual knowledge of Large Language Models (LLMs).

By Rinit Jain, Tirthraj Mahajan, Advait Joshi, Raviraj Joshi

llms benchmarks

arXiv Machine Learning

Aug 5

Beyond Initialization Loss: A Systematic Study of Token Embedding Initialization Strategies for LLM Vocabulary Extension

arXiv:2608. 03494v1 Announce Type: cross Abstract: Vocabulary extension is an efficient way to adapt pretrained large language models (LLMs) to new languages, but the initialization of newly added token embeddings can strongly affect continued pre-training (CPT) efficiency.

By Raviraj Joshi, Utkarsh Vaidya, Sanjay Singh Chauhan, Niranjan Wartikar

llms rag

Hugging Face Trending Papers

Aug 6

Sparse Mutual Information Graph Averaging for Improving Random Indexing Embeddings

Sparse word embedding pipelines can avoid dense co-occurrence matrix materialization, dense factorization, and gradient training while still relying on sparse global corpus statistics. This paper studies Random Indexing (RI) vectors refined by weighted averaging on a sparse Positive Pointwise Mutual Information (PPMI) graph.

rag nlp efficiency

arXiv Machine Learning

Jul 28

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis

arXiv:2607. 23319v1 Announce Type: cross Abstract: Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian languages.

By Poornima Kumaresan, Pavithra Muruganantham, Lakshmi Rajendran, Santhosh Sivasubramani

llms nlp benchmarks

Related stories