Machine translation is tough to evaluate, partly because most of what you throw at is too easy. That doesn't at all mean that translation is solved; we're just not doing a good job finding interesting inputs.
Come do a PhD with me at Columbia!
My lab tackles basic problems in alignment, interpretability, safety, and capabilities of language systems. If you love adventuring in model internals and behaviors---to understand and improve---let's do it together!
pic: a run in central park
🗺️ Are we making our #LLMs multilingual, or anglocentric?
Much work brings languages closer to English, but that comes at the cost of crucial #cultural nuance.
@h__j___han tackles this trade-off with surgical steering, adapting LLMs to cultural contexts at inference time.
Lots of work on cross-lingual alignment encourages multilingual LLMs to generalize knowledge across languages.
But this push for uniformity creates a tension: what happens to knowledge that should remain local?
We look into this trade-off of transfer and cultural erasure:🧵
Our Google Translate team is bringing a strong presence to #ACL2025 in Vienna this week! 🇦🇹 My group is excited to present several of our latest papers. 👇 Don't miss them!
Two new datasets from Google Translate targeting high and low resource languages!
WMT24++: 46 new en->xx languages to WMT24, bringing the total to 55
SMOL: 6M tokens for 115 very low-resource languages
WMT24++: huggingface.co/datasets/googl…
SMOL: huggingface.co/datasets/googl…
🚨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/2502.12404…
Data: huggingface.co/datasets/googl…
Thrilled to share our latest findings on data contamination, from my internship at @Google! We trained almost 90 Models on 1B and 8B scales with various contamination types using machine translation as our task and analyze the impact of contamination.
arxiv.org/abs/2501.18771
🚀 We have just released bfloat16 variants of all 3 MetricX-24 models, offering nearly identical performance to their float32 counterparts, but with a 50% smaller memory footprint. ✨ We hope this makes the XL and XXL models more accessible!
🔗 GitHub: github.com/google-researc…
🌐 Meet MetricX-24, our SOTA machine translation evaluation metric and a successor to the successful MetricX-23. 🚀 Now open-source in PyTorch/Transformers! 🎉 Ready to take this top performer in the WMT24 Metrics Shared Task for a spin?
🔗 Code: github.com/google-researc…
🌐 Meet MetricX-24, our SOTA machine translation evaluation metric and a successor to the successful MetricX-23. 🚀 Now open-source in PyTorch/Transformers! 🎉 Ready to take this top performer in the WMT24 Metrics Shared Task for a spin?
🔗 Code: github.com/google-researc…
LLMs are typically evaluated w/ automatic metrics on standard test sets, but metrics + test sets are developed independently. This raises a crucial question: Can we design automatic metrics specifically to excel on the test sets we prioritize? Answer: Yes!
arxiv.org/abs/2411.15387
@psingh522 Unfortunately this role requires that you are enrolled in a PhD program. But there are plenty of roles at Google for Master's students that you can find on the Google Careers page buildyourfuture.withgoogle.com/internships
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/…
369 Followers 754 FollowingActionable interpretability for (M)LLMs/Agent
CS PhD student @UMDCS
Prev: @UpennNLP
Rednote: https://t.co/offEkZOx7K
Intuition is all you need
323 Followers 2K Following🤖 AI @CompSciOxford @Berkeley_EECS @twosigma @cohere etc.
🤓 Social NLP (NLP x Societal Impacts)
🔍 Almost everywhere on the internet @elleismatic
8K Followers 7K FollowingCenter for Language and Speech Processing at @JohnsHopkins #NLProc #MachineLearning #AI https://t.co/6IXR5OSQtw
@[email protected]
953 Followers 329 FollowingPostdoc @Mila_Quebec @McGill_NLP 🇨🇦 PhD from @Edin_CDT_NLP 🏴 memorization vs generalization x (non-)compositionality x interpretability. she/her
261 Followers 852 FollowingML engineer at Apple. PhD in Neural Machine Translation. Background in ML, data science and SW engineering. Chinese lang enthusiast. Life-long learner. 学无止境
1.1M Followers 172 FollowingNobel Laureate. Co-Founder & CEO @GoogleDeepMind - working on AGI. Solving disease @IsomorphicLabs. Trying to understand the fundamental nature of reality.
40K Followers 122 FollowingMechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
9K Followers 52 FollowingThe official account of the Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics.
2K Followers 55 FollowingChief AI Scientist, Oracle, and the Eduardo D. Glandt Distinguished Professor, CIS, University of Pennsylvania. Former VP/Distinguished Scientist, AWS AI Labs.
316 Followers 2K FollowingAnyone living in an anyhow town. Cryptic crossword setter Gussalufz for #TheHinduCrossword and elsewhere. @[email protected] & @viresh.bsky.social
2K Followers 2K FollowingMachine translation research for big tech and big academia and director of the @aclanthology. Tweets here are mostly personal.