As Sweden's national center for applied AI, AI Sweden is looking for a master thesis student to join their NLU team. The project focuses on evaluating synthetic data generation strategies for delta learning, specifically to address the challenge of "translationese" artifacts in machine-translated data used for training Large Language Models (LLMs). The goal is to investigate if delta learning, using Direct Preference Optimization (DPO), can be used to synthesize documents that differ only in fluency, thereby steering models towards better fluency without negatively impacting other capabilities. The project involves a literature study, implementation of controlled DPO training runs, and evaluation using standard benchmarks.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Entry Level