Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Salhan, Suchir, Gu, Hongyi, Rooein, Donya, Galvan-Sosa, Diana, Gaudeau, Gabrielle, Caines, Andrew, Yuan, Zheng, Buttery, Paula
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909865165717504
author Salhan, Suchir
Gu, Hongyi
Rooein, Donya
Galvan-Sosa, Diana
Gaudeau, Gabrielle
Caines, Andrew
Yuan, Zheng
Buttery, Paula
author_facet Salhan, Suchir
Gu, Hongyi
Rooein, Donya
Galvan-Sosa, Diana
Gaudeau, Gabrielle
Caines, Andrew
Yuan, Zheng
Buttery, Paula
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_20411
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction
Salhan, Suchir
Gu, Hongyi
Rooein, Donya
Galvan-Sosa, Diana
Gaudeau, Gabrielle
Caines, Andrew
Yuan, Zheng
Buttery, Paula
Computation and Language
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.
title Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction
topic Computation and Language
url https://arxiv.org/abs/2510.20411