Multilingual Representation Workshop @ EMNLP 2026

Not satisfied with your ARR Meta-Reviews? Don't worry, give your work another chance by submitting it to the MRL Workshop at @emnlpmeeting! We also accept papers reviewed in past ARR cycles, deadline on Sept 4! #EMLNP #NLP

🎤 Speaker lineup drop! The MRL 2026 Workshop is bringing academia and industry together: @afaji.bsky.social , MBZUAI @mdlhx.bsky.social , KU Leuven @jumelet.bsky.social , Uni of Groningen Ahmet Üstün, Cohere See you all this October in Budapest! #EMNLP #MRL2026

After the enthusiasm of the shared task last year, we are running another shared task to create a community-made, culturally relevant multilingual benchmark! The deadline to contribute is August 1 AoE. See more details below.

You can fill in this form to receive updates on the project and get information about how to get involved: docs.google.com/forms/d/e/1F...

After the enthusiasm of the shared task last year, we are running another shared task to create a community-made, culturally relevant multilingual benchmark! The deadline to contribute is August 1 AoE. See more details below.

This year, the task will be question and answers in the style of ECLeKTic. Contributors are to compose questions that only people from a particular country or region are likely to know and questions should be culture- and language-specific.

We are releasing an expanded version of Global PIQA! It now covers 141 language varieties and includes parallel and non-parallel splits. We are also releasing an updated preprint.

Thank you to all of the authors who made this dataset possible!

We are releasing an expanded version of Global PIQA! It now covers 141 language varieties and includes parallel and non-parallel splits. We are also releasing an updated preprint.

Across all the best models and systems, there are steep performance drops for lower-resource languages and under-represented regions, especially Subsaharan Africa.

We are releasing an expanded version of Global PIQA! It now covers 141 language varieties and includes parallel and non-parallel splits. We are also releasing an updated preprint.

We created a new parallel split, where we created an original dataset and machine translated it into 131 languages, and contributors corrected those translations. This split can be used to better compare performance across languages.

We are releasing an expanded version of Global PIQA! It now covers 141 language varieties and includes parallel and non-parallel splits. We are also releasing an updated preprint.

📢 Call for Papers: 6th Multilingual Representation Learning Workshop at EMNLP in Budapest, Hungary! Join us and submit your works relating to multilingual NLP Speakers to be announced, so stay tuned! 👀 More info in the CFP: 🔗 sigtyp.github.io/ws2026-mrl.html

This afternoon, @catherinearnett.bsky.social presented the result of the shared task and presented the best contribution awards. Congratulations to all contributors!

The second is 7PERFECTION, a dataset for seven Nigerian languages!

This afternoon, @catherinearnett.bsky.social presented the result of the shared task and presented the best contribution awards. Congratulations to all contributors!

We would like to recognize three honorable mention submissions. Great work!

We have kicked off proceedings with some brief opening remarks from @catherinearnett.bsky.social

Join us in hall C3 at posters 137-168 for our in-person poster session. Join us online on Zoom via Underline for our virtual poster session!

We have kicked off proceedings with some brief opening remarks from @catherinearnett.bsky.social

@kellymarchisio.bsky.social from Cohere presents “Building Multilingual LLMs in Industry”, sharing insights on training multilinguality at scale!

Introducing Global PIQA, a new multilingual benchmark for 100+ languages. This benchmark is the outcome of this year’s MRL shared task, in collaboration with 300+ researchers from 65 countries. This dataset evaluates physical commonsense reasoning in culturally relevant contexts.

It’s not too late to get involved! Until early 2026, we will be accepting submissions for languages not already represented in Global PIQA. If you’re interested, please fill out this form and we will contact you with details! docs.google.com/forms/d/e/1F...

Introducing Global PIQA, a new multilingual benchmark for 100+ languages. This benchmark is the outcome of this year’s MRL shared task, in collaboration with 300+ researchers from 65 countries. This dataset evaluates physical commonsense reasoning in culturally relevant contexts.

The top proprietary models achieve ~90% accuracy, which falls short of human accuracy (~95%). The best open models perform significantly worse, with the best open model performance from Gemma 3 (27B) at 82.4%.

Introducing Global PIQA, a new multilingual benchmark for 100+ languages. This benchmark is the outcome of this year’s MRL shared task, in collaboration with 300+ researchers from 65 countries. This dataset evaluates physical commonsense reasoning in culturally relevant contexts.

Global PIQA includes subsets for 116 unique language varieties. These cover five continents, 14 language families, and 23 writing systems. Over 50% of examples reference local foods, customs, traditions, or other culturally-specific elements.

This year MRL is also accepting papers that have been submitted to ARR and have received reviews and a metareview! Submit your papers by September 23rd! See the workshop website for details on how to submit ⬇️

We have over 200 volunteers now for 90+ languages! We are hoping to expand the diversity of our language coverage and are still looking for participants who speak these languages. Check out how to get involved below, and please help us spread the word!

If you plan to participate, fill in this google form so we can better plan the shared task: forms.gle/zxhpCfL6wvBz...