Tootfinder

Once Upon a Time: Interactive Learning for Storytelling with Small Language Models
Jonas Mayer Martins, Ali Hamza Bashir, Muhammad Rehan Khalid, Lisa Beinborn
https://arxiv.org/abs/2509.15714

Once Upon a Time: Interactive Learning for Storytelling with Small Language Models
Children efficiently acquire language not just by listening, but by interacting with others in their social environment. Conversely, large language models are typically trained with next-word prediction on massive amounts of text. Motivated by this contrast, we investigate whether language models can be trained with less data by learning not only from next-word prediction but also from high-level, cognitively inspired feedback. We train a student model to generate stories, which a teacher model…