Unbabel Releases New Open-Source Large Language Model, The First LLM Fine Tuned to Predict Translation Quality

september 26, 2023

The state-of-the-art large language model (LLM) leads to increasingly accurate translations, supporting global expansion while saving time and money for businesses 

SAN FRANCISCO – september 26, 2023 – Unbabel, the AI-powered Language Operations (LangOps) platform that helps businesses deliver multilingual customer experience at scale, today announced the public release of its new open-source Large Language Model (LLM), CometKiwi XL and XXL, specially designed to predict translation quality. As the first LLM fine tuned for translation quality, CometKiwi offers exceptional performance and unprecedented quality estimation capabilities – contributing to increasingly accurate translations and improved cost savings while supporting global expansion. 

Even with its recent rapid advancements, AI translation is not always 100% accurate, especially in complex use cases. Additionally, with the explosion of machine translation products trained on different data sets, some models perform better than others for certain use cases. There is no best MT product in the market. This puts up barriers for businesses trying to efficiently translate and localize content for a global audience. Unbabel’s CometKiwi solves these problems by detecting and scoring translation quality, letting businesses determine when human intervention is appropriate and necessary, and when they can benefit from the efficiency of machine automation. 

“By making these models available to the public, our goal is to promote collaboration, facilitate knowledge sharing, and drive further advancements in quality estimation techniques,” said João Graça, Co-Founder and Chief Technology Officer of Unbabel. “We firmly believe that CometKiwi will make a significant contribution to the growth and innovation of the machine translation field as a whole.”

Supporting up to 100 languages, CometKiwi XL and XXL are the largest QE systems ever released with 3.5B and 10.7B parameters respectively. Named after its open-source predecessors, OpenKiwi and COMET, both LLMs achieved first place in the WMT 2023 QE shared task, which included high resource language pairs such as Chinese-English and English-German as well as low resource language pairs such as Hebrew-English, English-Tamil, English-Telugu, among others. 

This LLM release is the first in a series of LLMs Unbabel is set to release. To stay tuned on new releases, visit www.unbabel.com.

About Unbabel
Unbabel eliminates language barriers so that businesses can thrive across cultures and geographies. The company’s Language Operations platform blends advanced artificial intelligence with humans in the loop, for fast, efficient, high-quality translations that get smarter over time. Unbabel helps enterprises grow into new global markets and builds customer trust by creating more consistent, high-quality multilingual customer experiences across marketing and customer service. Based in San Francisco, CA, Unbabel works with leading brands such as Booking.com, Nestle, Panasonic, Patagonia, and UPS, to communicate effortlessly with customers around the world, no matter what language they speak.

Media Contact:

Taylor Callis

Alloy on behalf of Unbabel

unbabel@alloycrew.com 

855.300.8209

About the Author

Profile Photo of Content Team
Content Team

Unbabel’s Content Team is responsible for showcasing Unbabel’s continuous growth and incredible pool of in-house experts. It delivers Unbabel’s unique brand across channels and produces accessible, compelling content on translation, localization, language, tech, CS, marketing, and more.

DeutschFrançaisNLdanskSvenskaEnglish