Raphaël Merx

PhD @UniMelb | Tech Lead @CatalpaDev
Based in 🇮🇩, worked in🇹🇱 🇵🇬
AI, languages, governance, in no particular (world) order

[Raphaël Merx @RaphaelMerx]

@ivrik Kat, I'm infinitely sad reading this. May you, Andreas, and your son, find the strength to go through this, and may Lea continue her loving life in a better world.

[Raphaël Merx @RaphaelMerx]

https://t.co/0PqJBIxRbN

[Raphaël Merx @RaphaelMerx]

Our #WMT2025 paper got accepted 🙌
We release a dataset for health low-res MT... and find that Gemini 2.5 beats NLLB 54B, if given full document context.

Seeya in Suzhou!

[Catherine Arnett @linguist_cat]

Did you know?

❌77% of language models on @huggingface are not tagged for any language
📈For 95% of languages, most models are multilingual
🚨88% of models with tags are trained on English

In a new blog post, @tylerachang and I dig into these trends and why they matter! 👇

[Raphaël Merx @RaphaelMerx]

@davlanade @SenyuLiReal @alabi_jesujoba Really cool work, the AfriDoc-MT paper in particular is a trove of interesting findings on doc Vs sent level translation in low-res MT

[Raphaël Merx @RaphaelMerx]

paper: https://t.co/e8mIA9e5EC
demo: https://t.co/jlYphZa9h6

Grateful for all the help and advice from my supervisors Hanna Suominen, Nick Thieberger, Trevor Cohn, Katerina Vylomova, and special thanks to Maluk Timor & Lois Hong for the great joint work!

[Raphaël Merx @RaphaelMerx]

in Vienna for ACL, presenting Tulun, a system for low-resource in-domain translation, using LLMs

Working w 2 real use cases: medical translation into Tetun 🇹🇱 & disaster relief speech translation in Bislama 🇻🇺

[Kat Vylomova (कत् विलोमोव) 🕊️ @ivrik]

✨TULUN: Transparent and Adaptable Low-resource Machine Translation
By: Raphael Merx, Hanna Suominen, Lois Yinghui Hong, Nick Thieberger, Trevor Cohn, Kat Vylomova
Paper: https://t.co/Dn499KkhIO
Demo: https://t.co/y4Hr7397r3

#ACL2025NLP #NLProc #ACL2025

[Raphaël Merx @RaphaelMerx]

@YasminMoslem @AdaptCentre @tcddublin @Huawei Congrats Yasmin!

[Raphaël Merx @RaphaelMerx]

@prajdabre1 must be stressful... I'm sure you'll find something good though, smart driven people like you always land on their feet!

[Raphaël Merx @RaphaelMerx]

@yanmeg_build there's curse in Cursor for a reason

[Raphaël Merx @RaphaelMerx]

@prajdabre1 @geoffreyhinton @JeffDean @OriolVinyalsML Whoa that's very cool!

Didn't think I'd meet Taylor series approximation again in my lifetime

[Raphaël Merx @RaphaelMerx]

@yanmeg_build Legit good, became aware of the Trudeau resignation through this

[Raphaël Merx @RaphaelMerx]

@jlibovicky Enjoyed reading this, thanks for sharing!

[Raphaël Merx @RaphaelMerx]

Our paper on generating bilingual example sentences with LLMs got best paper award @altanlp !

https://t.co/pAULq5bv5f

We work with French / Indonesian / Tetun, find that annotators don't agree about what's a "good example", but that LLMs can align with a specific annotator.

[Raphaël Merx @RaphaelMerx]

@KushalTatariya @akulmizev @EstherPloeger @mmbollmann @johannesbjerva @heather_nlp @mdlhx @lagom_nlp Really nice paper, definitely saving this as inspiration for work on data quality!

For §5, you maybe you'd have seen more correlation btw quality & performance on NLG tasks, instead of NLU? As NLG would suffer from low-quality training data, more than NLU, I think?

[Raphaël Merx @RaphaelMerx]

@zouharvi Cool work, appreciate the video, and fire poster! Can I ask what you used to design it?

[Raphaël Merx @RaphaelMerx]

@prajdabre1 @NeurIPSConf Enjoy precious moments with family, congrats to all 3 of you!

[Raphaël Merx @RaphaelMerx]

@sethjsa @davidstap @diwuNLP @c_monz @illc_amsterdam @ltl_uva Super interesting!

In a similar vein, we studied MT using LLMs w sentences from a language manual for Mambai, and found that while scores were decent on test sentences sampled from the manual, it collapsed on sentences translated by a native speaker: https://t.co/vbFqG4xUKF

[Raphaël Merx @RaphaelMerx]

@prajdabre1 So cool Raj! Your mom can now say she's made two significant contributions to the NLP community, research and a researcher

[Eleftheria Briakou @ebriakou]

Translation is a complex task involving pre-translation research and post-translation stages. Can #LLMs handle this process step-by-step, relying solely on their internal knowledge?

✨We show that decomposing the translation process significantly improves #Gemini translation quality of long-form texts across all #WMT24 languages!

📜https://t.co/6JkRQwAsN2