דונורים ומקבלים: על תעבורה אסימטרית בין משימות ושפות עם תיקון פרמטרים-קצר

תקציר מקורי באנגליתarXiv:2511.13368v3 Announce Type: replace-cross Abstract: 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. We conduct a controlled LoRA fine-tuning study across multiple open-weight LLM families and scales, using a standardised grid of 11 languages and four benchmarks. We fine-tune each model on a single task-language source, then evaluate it on all other task-language target pairs to measure transfer. We decompose transfer into three regimes: (i) Matched-Task (Cross-Language), (ii) Cross-Task (Matched-Language), and (iii) Cross-Task (Cross-Language). Single-source fine-tuning yields a net positive uplift across regimes, but the gains are strongly asymmetric. Ma