5 papers
A Toolbox for Improving Evolutionary Prompt Search
Daniel GrieÃhaber, Maximilian Kimmich, Johannes Maucher +1
Evolutionary prompt optimization has demonstrated effectiveness in refining prompts for LLMs. However, existing approaches lack robust operators and efficient evaluation mechanisms…
The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR
Injy Hamed, Ngoc Thang Vu, Nizar Habash
Code-switching, the act of alternating between languages, emerged as a prevalent global phenomenon that needs to be addressed for building user-friendly language technologies. A ma…
Towards Zero-Shot, Controllable Dialog Planning with LLMs
Dirk Väth, Ngoc Thang Vu
Recently, Large Language Models (LLMs) have emerged as an alternative to training task-specific dialog agents, due to their broad reasoning capabilities and performance in zero-sho…
A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions
Injy Hamed, Caroline Sabty, Slim Abdennadher +3
Language in the Arab world presents a complex diglossic and multilingual setting, involving the use of Modern Standard Arabic, various dialects and sub-dialects, as well as multipl…
Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses
Chia-Yu Li, Ngoc Thang Vu
Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial a…