Skip to content

Author

Fajri Koto

We have 6 of 50 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Oct 2025

Parallel Tokenizers: Rethinking Vocabulary Design in Cross-Lingual Transfer of Low-Resource Languages

Parallel tokenizers are introduced, a new framework that first trains tokenizers monolingually and then aligns their vocabularies exhaustively using bilingual dictionaries or word-to-word translation to enforce a shared semantic space across languages while naturally improving fertility balance.

Muhammad Dehan Al Kautsar, Fajri Koto · 0 citations

Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems

This work introduces Sci-Rho (Science Rhobustness), a dynamic benchmark for visually-grounded STEM problems spanning five subjects and seven languages, comprising 4,242 problem templates crafted by domain experts, including Olympiad medalists.

Muhammad Falensi Azmi, Ikhlasul Akmal Hanif, Vallerie Alexandra Putra et al. · 0 citations
Jul 2026

CultureTalk-ID: A Multi-Task Dialogue Benchmark for Cultural Commonsense in Indonesian Local Languages

CultureTalk-ID is introduced, the first dialogue-based benchmark for cultural commonsense in Indonesian and its local languages, comprising 4,496 culturally grounded dialogues across 11 languages and 13 culturally salient topics, curated through a multi-stage human pipeline with native speakers to ensure authenticity.

Muhammad Dehan Al Kautsar, Salsabila Zahirah Pranida, Bilal Elbouardi et al. · 0 citations

Cultural Benchmarking of LLMs in MSA and Arabic Dialectal Dialogue

ArabCulture-Dialogue is introduced, a culturally grounded conversational dataset covering 13 Arabic-speaking countries, in both MSA and each country’s respective dialect, spanning 12 daily-life topics and 54 fine-grained subtopics, to address the performance gap between MSA and Arabic dialects.

M. Dehan, Aldry Kautsar, SaeedAlmheiri et al. · 0 citations
Preprint Jul 2026

Jais 2: A Family of Arabic-Centric Open Large Language Models

Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest...

Mohamed Anwar, A. Freihat, George Ibrahim et al. · 3 citations
#artificial intelligence Preprint Sep 2026

Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close

When a question has valid answers under different normative frameworks, a language model must decide which framework to use and whether it can answer correctly within it. We call this setting normative pluralism and study it in Islamic finance using a four-choice taxonomy that separates framework selection from within-...

R. Elbadry, Ahmed Heakl, Saeed Almheiri et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.