{"ID":2851109,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20411","arxiv_id":"2510.20411","title":"Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction","abstract":"Multi-turn dialogues between a child and a caregiver are characterized by a property called contingency - that is, prompt, direct, and meaningful exchanges between interlocutors. We introduce ContingentChat, a teacher-student framework that benchmarks and improves multi-turn contingency in a BabyLM trained on 100M words. Using a novel alignment dataset for post-training, BabyLM generates responses that are more grammatical and cohesive. Experiments with adaptive teacher decoding strategies show limited additional gains. ContingentChat demonstrates the benefits of targeted post-training for dialogue quality and indicates that contingency remains a challenging goal for BabyLMs.","short_abstract":"Multi-turn dialogues between a child and a caregiver are characterized by a property called contingency - that is, prompt, direct, and meaningful exchanges between interlocutors. We introduce ContingentChat, a teacher-student framework that benchmarks and improves multi-turn contingency in a BabyLM trained on 100M word...","url_abs":"https://arxiv.org/abs/2510.20411","url_pdf":"https://arxiv.org/pdf/2510.20411v1","authors":"[\"Suchir Salhan\",\"Hongyi Gu\",\"Donya Rooein\",\"Diana Galvan-Sosa\",\"Gabrielle Gaudeau\",\"Andrew Caines\",\"Zheng Yuan\",\"Paula Buttery\"]","published":"2025-10-23T10:29:23Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}