EAMT 2026 - European Association for Machine Translation Conference in Tilburg, Netherlands

Multilingual large language models (LLMs) aim towards robust natural language understanding across diverse languages, yet their performance significantly degrades on low-resource languages. This work explores whether existing techniques to identify language-specific neurons can be leveraged to enhance cross-lingual task performance of lowresource languages. We conduct detailed experiments covering existing language-specific neuron identification techniques (such as Language Activation Probability Entropy and activation probability-based thresholding) and neuron-specific LoRA fine-tuning with models like Llama 3.1 and Mistral Nemo. We find that such neuron-specific interventions are insufficient to yield cross-lingual improvements on downstream tasks (XNLI, XQuAD) in lowresource languages. This study highlights the challenges in achieving cross-lingual generalization and provides critical insights for multilingual LLMs.

Large Language Models (LLMs) have become an increasingly important tool in research and society at large. While LLMs are regularly used all over the world by experts and lay-people alike, they are pre...

Last year, we shared what we had learned from developing and piloting Flying Colors, an innovative approach to tech-enabled project-based…

Background Clinical examination and functional assessment are often the first steps to assess outcome of clubfoot treatment. Clinical photographs may be an adjunct used to assess treatment outcomes in...