mlsanityData to 7 Oct 2026

Introducing DictaLM -- A Large Generative Language Model for Modern Hebrew

arXiv 2309.14568 ↗First posted 25 Sep 2023cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

We present DictaLM, a large-scale language model tailored for Modern Hebrew. Boasting 7B parameters, this model is predominantly trained on Hebrew-centric data. As a commitment to promoting research and development in the Hebrew language, we release both the foundation model and the instruct-tuned model under a Creative Commons license. Concurrently, we introduce DictaLM-Rab, another foundation model geared towards Rabbinic/Historical Hebrew. These foundation models serve as ideal starting points for fine-tuning various Hebrew-specific tasks, such as instruction, Q&A, sentiment analysis, and more. This release represents a preliminary step, offering an initial Hebrew LLM model for the Hebrew NLP community to experiment with.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 9 of its 12 references that are in the map. First posted on arXiv 25 Sep 2023.

Builds on

9 of 12 references.

References · 9

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  3. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2020GLU Variants Improve Transformercited by 1,724
  6. 2020Neural Modeling for Named Entities and Morphology (NEMO^2)cited by 26
  7. 2021ParaShoot: A Hebrew Question Answering Datasetcited by 12
  8. 2023HeRo: RoBERTa and Longformer Hebrew Language Modelscited by 12
  9. 2020Improving Low Compute Language Modeling with In-Domain Embedding Initialisationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.