SOURCE-LINKED INTELLIGENCE

Which Forms of Caregiver Feedback Support Grammar Learning? A Reinforcement-Learning Study of Child-Like Language Models

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Social interaction is central to children's language learning, but the effects of different forms of caregiver feedback are difficult to isolate in naturalistic data. We use child-like language models as controlled learners to test which forms of feedback support grammatical development. Small GPT-2-style models are pretrained on child-directed language from CHILDES, then fine-tuned with reinforcement learning using reward models trained to capture four feedback types: communicative feedback, structural alignment, semantic contingency, and affective feedback. Reward fine-tuning yields limited

Read original source ↗ Open in workspace

recordType

paper

region

Global