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

• URL: http://arxiv.org/abs/2609.08576v1
• Date: Tue, 08 Sep 2026 11:12:11 GMT
• Title: Which Forms of Caregiver Feedback Support Grammar Learning? A Reinforcement-Learning Study of Child-Like Language Models
• Abstract summary: Social interaction is central to children's language learning.<n>We use child-like language models to test which forms of feedback support grammatical development.
• Score: 5.474041566740772
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 gains on minimal-pair evaluations, but clearer effects in free generation. Structural alignment produces the strongest improvements in grammaticality, providing a novel, plausible mechanistic account of how this feedback can support grammar learning. Communicative feedback yields more moderate gains. In contrast, semantic contingency and affective feedback do not improve grammaticality, although further analyses suggest that they may support other aspects of language learning beyond grammar. These results suggest that different forms of caregiver feedback make complementary contributions to language learning.

Related papers

• Once Upon a Time: Interactive Learning for Storytelling with Small Language Models [1.8012666291588018]
  We investigate whether language models can be trained with less data by learning from high-level, cognitively inspired feedback.<n>We train a student model to generate stories, which a teacher model rates on readability, narrative coherence, and creativity.<n>We find that the high-level feedback is highly data efficient: With just 1 M words of input in interactive learning, storytelling skills can improve as much as with 410 M words of next-word prediction.
  arXiv  Detail & Related papers  (2025-09-19T07:45:34Z)
• Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models [49.22720751953838]
  We propose a method for training language models in an interactive setting inspired by child language acquisition.<n>In our setting, a speaker attempts to communicate some information to a listener in a single-turn dialogue and receives a reward if communicative success is achieved.
  arXiv  Detail & Related papers  (2025-05-09T11:48:36Z)
• Developmental Predictive Coding Model for Early Infancy Mono and Bilingual Vocal Continual Learning [69.8008228833895]
  We propose a small-sized generative neural network equipped with a continual learning mechanism.<n>Our model prioritizes interpretability and demonstrates the advantages of online learning.
  arXiv  Detail & Related papers  (2024-12-23T10:23:47Z)
• Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models [31.006803764376475]
  Semantic and syntactic bootstrapping posit that children use their prior knowledge of one linguistic domain, say syntactic relations, to help later acquire another, such as the meanings of new words. Here, we argue that they are instead both contingent on a more general learning strategy for language acquisition: joint learning. Using a series of neural visually-grounded grammar induction models, we demonstrate that both syntactic and semantic bootstrapping effects are strongest when syntax and semantics are learnt simultaneously.
  arXiv  Detail & Related papers  (2024-06-17T18:01:06Z)
• Learning Language Structures through Grounding [8.437466837766895]
  We consider a family of machine learning tasks that aim to learn language structures through grounding. In Part I, we consider learning syntactic parses through visual grounding. In Part II, we propose two execution-aware methods to map sentences into corresponding semantic structures. In Part III, we propose methods that learn language structures from annotations in other languages.
  arXiv  Detail & Related papers  (2024-06-14T02:21:53Z)
• Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations [15.394018604836774]
  We introduce a trial-and-demonstration (TnD) learning framework that incorporates three components: student trials, teacher demonstrations, and a reward conditioned on language competence at various developmental stages.<n>Our experiments reveal that the TnD approach accelerates word acquisition for student models of equal or smaller numbers of parameters, and we highlight the significance of both trials and demonstrations.<n>Our findings suggest that interactive language learning, with teacher demonstrations and active trials, can facilitate efficient word learning in language models.
  arXiv  Detail & Related papers  (2024-05-22T16:57:02Z)
• Visual Grounding Helps Learn Word Meanings in Low-Data Regimes [47.7950860342515]
  Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension. But to achieve these results, LMs must be trained in distinctly un-human-like ways. Do models trained more naturalistically -- with grounded supervision -- exhibit more humanlike language learning? We investigate this question in the context of word learning, a key sub-task in language acquisition.
  arXiv  Detail & Related papers  (2023-10-20T03:33:36Z)
• Training Language Models with Language Feedback at Scale [50.70091340506957]
  We introduce learning from Language Feedback (ILF), a new approach that utilizes more informative language feedback. ILF consists of three steps that are applied iteratively: first, conditioning the language model on the input, an initial LM output, and feedback to generate refinements. We show theoretically that ILF can be viewed as Bayesian Inference, similar to Reinforcement Learning from human feedback.
  arXiv  Detail & Related papers  (2023-03-28T17:04:15Z)
• Chain of Hindsight Aligns Language Models with Feedback [62.68665658130472]
  We propose a novel technique, Chain of Hindsight, that is easy to optimize and can learn from any form of feedback, regardless of its polarity. We convert all types of feedback into sequences of sentences, which are then used to fine-tune the model. By doing so, the model is trained to generate outputs based on feedback, while learning to identify and correct negative attributes or errors.
  arXiv  Detail & Related papers  (2023-02-06T10:28:16Z)
• Leveraging Pre-trained Language Model for Speech Sentiment Analysis [58.78839114092951]
  We explore the use of pre-trained language models to learn sentiment information of written texts for speech sentiment analysis. We propose a pseudo label-based semi-supervised training strategy using a language model on an end-to-end speech sentiment approach.
  arXiv  Detail & Related papers  (2021-06-11T20:15:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.