Markus Freitag retweeted
Very excited to announce Gemini 4 Argon! It delivers frontier performance across coding, knowledge work and cyber defense capabilities. The model is well-rounded and has great writing quality. The team has been hard at work producing this and we've all enjoyed using it everyday.
Lots of discussion out there about our next model(!), so I wanted to give an early look as soon as possible. Introducing Gemini 4 Argon!
It shows frontier performance in complex workflows, cyber defense and software engineering. Teams are using it extensively at Google, from coding to quantum computing, great feedback.
Here’s a look at the benchmarks:
Markus Freitag retweeted
I'm on the faculty job market for Fall 2027 assistant professorship. I work on the science of AI/NLP evaluation, which is currently undergoing a crisis:
We were asking one question a year ago: "Can we trust LLMs to build and grade their own benchmarks"? We tested frontier models on automated LLM benchmarking. The result? Every single model ranks itself #1 on benchmarks it generates (arxiv.org/abs/2509.26600). Our work has been accepted to EMNLP 2026 Main!
Markus Freitag retweeted
Happy to share CollabEval, recent(-ish) work from @GoogleDeepMind and @GoogleResearch that can be used to improve the statistical efficiency of model evaluation by exploiting correlations between historical evals of different models on the same tasks.
arxiv.org/pdf/2607.05046
Markus Freitag retweeted
🎓Completed a PhD on Machine Translation, multilingual, or cross-lingual NLP?
Nominate a standout thesis (or your own!) for the AMTA Best Thesis Award. Winner gets $1000, an invited talk at #AMTA2026 & more.
🗓️ Deadline: 15 May 2026
ℹ️Info: amtaweb.org/amta-2026-first-…
#MT #NLP #PhD
Markus Freitag retweeted
Announcing TranslateGemma, a new collection of open translation models built on Gemma 3. Learn more 👇
Replying to @googleaidevs
TranslateGemma outperforms models twice its size, has been trained and evaluated on 55 language pairs to ensure high-quality performance, and uses a specialized two-stage fine-tuning process that distills the knowledge of Gemini models into an open architecture.
Markus Freitag retweeted
Check out TowerVision, a multilingual multicultural VLM powered by the @sardine_lab_it. Great work led by @Guilherme_PT1 and @psanfernandes! Bonus: TowerVideo, kudos to @Saul_Santos1997!
Replying to @Guilherme_PT1
This project is the result of an amazing collaboration between researchers:
Authored by: @Guilherme_PT1 @psanfernandes @Saul_Santos1997 @SonalSannigrahi @ManosZaranis @nunonmg @amin_farajian @PierreColombo6 @gneubig @andre_t_martins
Markus Freitag retweeted
Every month, people use Google to translate around 1 trillion words. Today, we’re introducing a new AI-powered live translation experience in the Google Translate app, plus a new beta feature to help you practice new languages. Rolling out now on iOS + Android.
Markus Freitag retweeted
MT metrics excel at evaluating sentence translations, but struggle with complex texts
We introduce *TREQA* a framework to assess how translations preserve key info by using LLMs to generate & answer questions about them
arxiv.org/abs/2504.07583
(co-lead @swetaagrawal20)
1/15
Markus Freitag retweeted
.@Google and @imperialcollege researchers argue that translation quality can’t be captured 🛑 by a single metric and propose evaluating #AI #translation systems 🤖 on an accuracy-naturalness plane.
#xl8 #t9n #Google @GoogleAI @markuseful
slator.com/google-calls-for-…
Markus Freitag retweeted
😼SMOL DATA ALERT! 😼Anouncing SMOL, a professionally-translated dataset for 115 very low-resource languages! Paper: arxiv.org/pdf/2502.12301
Huggingface: huggingface.co/datasets/goog…
Markus Freitag retweeted
🚨New machine translation dataset alert! 🚨We expanded the language coverage of WMT24 from 9 to 55 en->xx language pairs by collecting new reference translations for 46 languages in a dataset called WMT24++
Paper: arxiv.org/abs/2502.12404v1
Data: huggingface.co/datasets/goog…
Markus Freitag retweeted
New application link! google.com/about/careers/app…
I am at EMNLP/WMT this week. Please come find me if you want to learn more about this role!
Interested in doing research on Google Translate and Gemini? Good news! I’m hiring for full-time roles on the Google Translate Research Team! Apply here: google.com/about/careers/app…
Markus Freitag retweeted
MT folks, welcome to try Translation Canvas system for analyzing translation performance. It is based on InstructScore, which not only provides a quality score but also fine-grained explanation for translation errors.
arxiv.org/abs/2410.10861
@WendaXu2 @siqi_ouyang
Replying to @LTIatCMU
Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems
by Chinmay Dandekar, Wenda Xu, Xi Xu, @siqi_ouyang, and @lileics
Session: Demo, Session 06, 10:30-12:00
arxiv.org/abs/2410.10861
Markus Freitag retweeted
🚀 Join the Gemini Multilinguality team @GoogleDeepMind 🌐 We’re looking for researchers passionate about making LLMs helpful for all. Dramatically improve model quality, coverage, and cultural relevance across hundreds of languages. #NLProc #MultilingualAI #i18n #LLMs boards.greenhouse.io/deepmin…
Markus Freitag retweeted
Despite growing interest in incorporating feedback to improve language models, most efforts focus only on sequence-level annotations.
Presenting Training with Annotations (TWA), a method to finetune on examples with span-level error annotations: arxiv.org/abs/2410.16509 (1/n)
Markus Freitag retweeted
📢 NAACL needs Reviewers & Area Chairs! 📝
If you haven't received an invite for ARR Oct 2024 & want to contribute, sign up by Oct 22nd!
➡️AC form: forms.office.com/r/8j6jXLfAS…
➡️Reviewer form: forms.office.com/r/cjPNtL9gP…
Please RT 🔁 and help spread the word! 🗣️
#NLProc @ReviewAcl
Markus Freitag retweeted
Interested in doing research on Google Translate and Gemini? Good news! I’m hiring for full-time roles on the Google Translate Research Team! Apply here: google.com/about/careers/app…
Markus Freitag retweeted
Google Translate now as Inuktut (Latin and Syllabics), Crimean Tatar (Latin script), Santali (Ol Chiki), Tshiluba, and French (Canada)!
Markus Freitag retweeted
Researchers from @Google reveal that verbose #LLMs, 🤖 which offer multiple translations 🔄 or refuse to translate, 🚫 pose significant challenges ⚠️ to traditional #MT evaluation frameworks.
#machinetranslation @ebriakou @ColinCherry @markuseful
slator.com/google-finds-refu…



























