Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
read the original abstract
We introduce Jais and Jais-chat, new state-of-the-art Arabic-centric foundation and instruction-tuned open generative large language models (LLMs). The models are based on the GPT-3 decoder-only architecture and are pretrained on a mixture of Arabic and English texts, including source code in various programming languages. With 13 billion parameters, they demonstrate better knowledge and reasoning capabilities in Arabic than any existing open Arabic and multilingual models by a sizable margin, based on extensive evaluation. Moreover, the models are competitive in English compared to English-centric open models of similar size, despite being trained on much less English data. We provide a detailed description of the training, the tuning, the safety alignment, and the evaluation of the models. We release two open versions of the model -- the foundation Jais model, and an instruction-tuned Jais-chat variant -- with the aim of promoting research on Arabic LLMs. Available at https://huggingface.co/inception-mbzuai/jais-13b-chat
This paper has not been read by Pith yet.
Forward citations
Cited by 10 Pith papers
-
HalluScore: Large Language Model Hallucination Question Answering Benchmark
HalluScore is a curated Arabic QA dataset with 827 questions, ground-truth evidence, and human annotations used to measure hallucination rates across 17 LLMs.
-
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
XL-SafetyBench is a new cross-cultural benchmark showing frontier LLMs decouple jailbreak robustness from cultural sensitivity while local models trade off attack success against neutral-safe rates in a near-linear pa...
-
LQM: Linguistically Motivated Multidimensional Quality Metrics for Machine Translation
LQM introduces a six-level linguistically motivated error taxonomy for MT evaluation and applies it via expert annotation to LLM outputs on a new 3,850-sentence multi-dialect Arabic corpus.
-
IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages
IndicGuard provides a culturally nuanced safety dataset for ten Indic languages and a fine-tuned Gemma-3-4B-IT model that outperforms CultureGuard on moderation tasks and generalizes to unseen low-resource languages.
-
ArabiGEE: A Hierarchical Taxonomy for Arabic Grammatical Error Explanation
ArabiGEE introduces the first hierarchical taxonomy for Arabic grammatical error explanation, with 27 error types, 140 correction types, and 324 explanations, applied to annotate corpora and evaluate LLMs.
-
The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs
Using a 1PL IRT model on real cultural questions across 13 locales, the study identifies a local-language knowledge-access advantage masked by lower proficiency in raw accuracy.
-
Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues
ArabCulture-Dialogue dataset shows LLMs perform worse on dialectal Arabic than Modern Standard Arabic across cultural reasoning, translation, and generation tasks.
-
Low-Resource Languages Jailbreak GPT-4
Translating unsafe inputs to low-resource languages jailbreaks GPT-4 at rates on par with or exceeding state-of-the-art attacks.
-
LLM-Based Financial Sentiment Analysis in Arabic: Evidence from Saudi Markets
Introduces a multi-stage Arabic financial sentiment pipeline that produces an 84K-sample corpus for company-level analysis tied to Saudi stock market behavior.
-
Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation
Residual-stream noise injection raises narrative diversity in Arabic educational stories while preserving reading-grade level, outperforming high-temperature sampling across five 7-9B models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.