2 papers
cs.CL2026
Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning
Kajetan Dymkiewicz, Ivan Vulic, Helen Yannakoudakis +3
Large language models (LLMs) perform strongly across tasks and languages, yet how improvements in one task or language affect other tasks and languages remains poorly understood. W…
cs.CL2024
Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models
Mor Ventura, Eyal Ben-David, Anna Korhonen +1
Text-To-Image (TTI) models, such as DALL-E and StableDiffusion, have demonstrated remarkable prompt-based image generation capabilities. Multilingual encoders may have a substantia…