2 papers
cs.CL2025
LatentPrompt: Optimizing Promts in Latent Space
Mateusz BystroÅski, Grzegorz Piotrowski, Nitesh V. Chawla +1
Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics…
cs.CL2025
SMOTExT: SMOTE meets Large Language Models
Mateusz BystroÅski, MikoÅaj HoÅysz, Grzegorz Piotrowski +2
Data scarcity and class imbalance are persistent challenges in training robust NLP models, especially in specialized domains or low-resource settings. We propose a novel technique,…