{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/ece44486\"></iframe>","width":"100%","height":180,"duration":1246,"description":"\n            🤗 Upvotes: 178 | cs.CL, cs.AI\n\n            Authors:\n            Khalil Hennara, Muhammad Hreden, Mohamed Motaism Hamed, Zeina Aldallal, Sara Chrouf, Safwan AlModhayan\n\n            Title:\n            Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model\n\n            Arxiv:\n            http://arxiv.org/abs/2505.17894v1\n\n            Abstract:\n            We introduce Mutarjim, a compact yet powerful language model for bidirectional Arabic-English translation. While large-scale LLMs have shown impressive progress in natural language processing tasks, including machine translation, smaller models. Leveraging this insight, we developed Mutarjim based on Kuwain-1.5B , a language model tailored for both Arabic and English. Despite its modest size, Mutarjim outperforms much larger models on several established benchmarks, achieved through an optimized two-phase training approach and a carefully curated, high-quality training corpus.. Experimental results show that Mutarjim rivals models up to 20 times larger while significantly reducing computational costs and training requirements. We also introduce Tarjama-25, a new benchmark designed to overcome limitations in existing Arabic-English benchmarking datasets, such as domain narrowness, short sentence lengths, and English-source bias. Tarjama-25 comprises 5,000 expert-reviewed sentence pairs and spans a wide range of domains, offering a more comprehensive and balanced evaluation framework. Notably, Mutarjim achieves state-of-the-art performance on the English-to-Arabic task in Tarjama-25, surpassing even significantly larger and proprietary models like GPT-4o mini. We publicly release Tarjama-25 to support future research and advance the evaluation of Arabic-English translation systems.\n            ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}