חשיבה רב-לשונית: מסגרת חדשה ללימוד מודלים לקוד-סוויץ'

תקציר מקורי באנגליתarXiv:2604.15490v2 Announce Type: replace Abstract: Recent developments in reasoning capabilities have enabled large language models to solve increasingly complex mathematical, symbolic, and logical tasks. Interestingly, while reasoning models are often trained to generate monolingual text, these models have also been observed to code-switch (i.e., mix languages). Prior works have either viewed code-switching as an undesirable error, attempted to control code-switching through modifications to input prompts or the output decoding process, or focus on narrow subsets of languages, domains, tasks, and models. We address these gaps by introducing the first linguistically and behaviorally motivated fine-tuning framework for identifying beneficial code-switched reasoning behaviors in large langu