Paper summary
Paper summary: Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model
Mutarjim is a 1.5B-parameter Arabic–English translation model that's reported to rival models up to 20× larger, plus Tarjama-25, a new 5,000-pair benchmark built to fix gaps in existing test sets.
- Careful two-phase training on a curated corpus lets a 1.5B model compete with much larger translators.
- The new benchmark targets three known problems: narrow domains, short sentences and English-source bias.