Hanna Yukhymenko

Excited to be joining #ACL2025NLP in Vienna 🇦🇹!
DM me if you would like to meet up and chat 👋

Announcing MamayLM, an efficient state-of-the-art Ukrainian LLM A Blog post by Institute for Computer Science, Artificial intelligence and Technology on Hugging Face

A powerful step for linguistic tech: ETH Zurich student Hanna Yukhymenko developed MamayLM – a Ukrainian #LLM fluent in 🇺🇦 & 🇬🇧, capturing language, culture & history. Supervised by Prof. Vechev & alumnus A. Alexandrov, in collab with INSAIT. bit.ly/3ED4o5k
@ayukh.bsky.social @ethzurich.bsky.social

It's just a game to these people

Шо?

1/1 complete

📢 Our benchmark on self-supervised learning for single-cell data🧬 is accepted at the #NeurIPS2024 SSL workshop. We take a first step towards establishing best practices for SSL methods for single-cell data, and benchmark 8 SSL methods on 3 downstream tasks across 8 datasets.

Watch me stalk Kaggle in Vancouver to get stickers

Is MMLU Western-centric? 🤔

As part of a massive cross-institutional collaboration:
🗽Find MMLU is heavily overfit to western culture
🔍 Professional annotation of cultural sensitivity data
🌍 Release improved Global-MMLU 42 languages

📜 Paper: arxiv.org/pdf/2412.03304
📂 Data: hf.co/datasets/Coh...

Going to #neurips2024 next week

Yes, I should have specified it before maybe :)

This means basically more publicly available materials, yes
For example, more ready-to-use data (e.g. web scraped texts) for LLM fine-tuning, more Ukrainian-native benchmarks for evals etc. This screenshot is from INCLUDE paper by Cohere which has Ukrainian exams in it, thus a new resource for eval🙂

Before I have seen many papers claiming Ukrainian language to be low-resource, even though there are ~40 mil UA speakers worldwide, so there should be a lot of proof to that
Since 2022 Ukrainian NLP effort has dramatically increased and the number of Ukrainian texts available online has increased

Цей день настав - Ukrainian is finally recognized as a mid-resource language 🇺🇦🦅🦅🦅

Exciting end of the year!
- Won the GraySwanAI jailbreaking challenge for harmful code generation
- Proud Ukrainian ambassador for Cohere4AI new Aya Expanse models
- Started my master thesis👩‍🍳🇺🇦👀
- Going to Vancouver🇨🇦 for @neuripsconf.bsky.social to chat about LLM privacy and SynthPAI

#neurips

Seems to be a hot take here: why are people getting mad about stuff they post *themselves* online? Your posts online are getting scraped all the time and you chose an open-source movement leader as a scapegoat.
Just initiate a discussion with HF about the "right to be forgotten" from GDPR

👋

Zaporizhzhia, a big Ukrainian city of almost one million, is under a massive drone attack. terrorism is russian culture.

LVE Repository We document and track vulnerabilities and exposures of large language models (LVEs).

One year of ChatGPT has shown incredible capabilities of LLMs. However, they still have lots of problems! The LVE project aims at addressing this - with LVEs we track LLM vulnerabilities and exposures in an open-source community-first approach.

Contribute and more info: lve-project.org
#NLP #LLM

Тред з корисними порадами для тих, хто щойно долучився. 🧵

Купила українські вареники в Швейцарії

🤙🫡

Як кажуть

Дякую за інвайт💅