top of page

As large language models increasingly shape the linguistic landscape, it has become ever more urgent to ensure that the voices of low-resource languages are not lost in the process. SilkRoadNLP is dedicated to advancing computational research and responsible AI for the Iranian linguistic family—a richly diverse group of languages spanning Iran, Afghanistan, Central and South Asia, and the Caucasus. Building robust datasets, tools, and evaluation frameworks for these languages is not only a technical priority, but a matter of cultural preservation and digital equity.

SilkRoadNLP: The first ACL forum on low-resource NLP and LLMs in the Iranian language family.

At its core, the workshop provides a collaborative platform for scholars, engineers, and community researchers to explore the linguistic, historical, and social dimensions of NLP for Iranian languages. These include Persian (Farsi)Dari, and Tajik, as well as KurdishPashtoBalochiGilakiMazandaraniLuriOssetic, and related varieties—many of which remain severely under-represented in computational research despite their deep literary and oral traditions.

The rise of foundation models brings both promise and peril: without deliberate inclusion, LLMs risk amplifying linguistic inequality and erasing local nuance. 

SilkRoadNLP responds to this moment by fostering a cross-disciplinary dialogue between NLP, linguistics, and cultural studies. We are working toward technologies that represent, rather than replace, the languages and communities of this vast region.

We invite researchers, practitioners, and community members to join us in shaping the future of multilingual AI for the Iranian linguistic family. 

SilkRoadNLP welcomes work on all aspects of NLP and large language models (LLMs) for Iranian languages— with a special focus on the low-resource languages—spanning resource creation, linguistic analysis, model adaptation, ethical and educational applications, and culturally grounded AI. Your contributions will help build the data, tools, and collaborations needed to ensure that these languages thrive in the age of LLMs.

1st Workshop on NLP and Large Language Models for the Iranian Language Family

March 28 or 29, 2026. Rabat, Morocco.
(Workshop Date to be confirmed)

co-located with
u8736419749_A_flowing_digital_caravan_across_the_Silk_Road_gl_9a3e9bc2-0ae5-46d8-84a0-e418

SilkRoadNLP 2026

bottom of page