paper-with-me

홈 › Papers

HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model

2026-05-11 · Noam Kayzer, Dan Revital, Ori Bar Joseph, Smadar Arvatz, Or Levi, Tal Geva, Shaltiel Shmidman, Amir DN Cohen, Noam Ordan, Omer Baruch, Kate Zinkovskaia, Zevi Apini, Sarel Weinberger arxiv

We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Training employs a three-phase easy-to-hard curriculum with continuous anti-forgetting anchoring, followed by supervised fine-tuning on 2 million bilingual Hebrew--English samples. The curriculum ordering alone yields a 3-point aggregate benchmark gain over the reversed configuration. Hebatron achieves a Hebrew reasoning average of 73.8\%, outperforming DictaLM-3.0-24B-Thinking (68.9\%) and remaining competitive with Gemma-3-27B-IT on GSM8K-HE and Israeli Trivia, while activating only 3B parameters per forward pass across a 30B-parameter model, delivering approximately 9 times higher inference throughput at native context lengths up to 65,536 tokens. To our knowledge, this is the first language-specific adaptation of the Nemotron-3 architecture for any target language, and the first open-weight Hebrew-specialized MoE model with native long-context support. Model weights are released openly to support further research in Hebrew and Semitic-language NLP.

📄 PDF Abstract BibTeX arXiv:2605.11255

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Phonikud: Hebrew Grapheme-to-Phoneme Conversion for Real-Time Text-to-Speech

2025-06-14 · Yakov Kolani, Maxim Melichov, Cobi Calev, Morris Alper

Real-time text-to-speech (TTS) for Modern Hebrew is challenging due to the language's orthographic complexity. Existing solutions ignore crucial phonetic features such as stress that remain underspecified even when vowel…

Grapheme-to-Phoneme Conversiontext-to-speechText to Speech

Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs

2026-02-02 · Shaltiel Shmidman, Avi Shmidman, Amir DN Cohen, Moshe Koppel arxiv

Open-weight LLMs have been released by frontier labs; however, sovereign Large Language Models (for languages other than English) remain low in supply yet high in demand. Training large language models (LLMs) for low-res…

HalleluBERT: Let Every Token That Has Meaning Bear Its Weight

2025-10-24 · Raphael Schmitt arxiv

Transformer-based models have advanced NLP, yet Hebrew still lacks a RoBERTa encoder that is trained at scale and released in both base and large variants. We present HalleluBERT, a RoBERTa-based encoder family trained f…

Multilingual Sequence-to-Sequence Models for Hebrew NLP

2022-12-19 · Matan Eyal, Hila Noga, Roee Aharoni, Idan Szpektor 외

Recent work attributes progress in NLP to large language models (LMs) with increased model size and large quantities of pretraining data. Despite this, current state-of-the-art LMs for Hebrew are both under-parameterized…

Decodernamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)

Adapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction Capabilities

2024-07-09 · Shaltiel Shmidman, Avi Shmidman, Amir DN Cohen, Moshe Koppel

Training large language models (LLMs) in low-resource languages such as Hebrew poses unique challenges. In this paper, we introduce DictaLM2.0 and DictaLM2.0-Instruct, two LLMs derived from the Mistral model, trained on …

Multilingual NLPQuestion AnsweringSentiment Analysis