Kazakhstani research at ACL 2025
The 63rd Annual Meeting of the Association for Computational Linguistics, ACL 2025, took place in Vienna from July 27 to August 1. It is one of the most prestigious conferences in NLP and AI!
The conference featured work by our compatriots and community residents. These papers expand the research foundation for building and evaluating LLMs in low-resource languages, with a particular focus on Kazakh:
- Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh — Nurkhan Laiyk, Daniil Orel, Maiya Goloburda
- KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan — Mukhammed Togmanov, Nurdaulet Mukhituly, Diana Turmakhan, Maiya Goloburda, Bekassyl Syzdykov, Nurkhan Laiyk
- Qorgau: Evaluating LLM Safety in Kazakh-Russian Bilingual Contexts — Maiya Goloburda, Nurkhan Laiyk, Diana Turmakhan, Mukhammed Togmanov, Askhat Sametov, Nurdaulet Mukhituly, Daniil Orel
- CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings — Daniil Orel
- RECALL: Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles — Zangir Iklassov
This is a landmark moment for Kazakhstan's entire AI community. Congratulations to the authors on reaching the global stage—we look forward to their next achievements!
Comments