Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations
Ziqiao Ma, Zekun Wang, Joyce Chai

TL;DR
This paper introduces a trial-and-demonstration framework for interactive language learning in neural models, demonstrating that social-like feedback accelerates word acquisition and improves learning efficiency.
Contribution
It presents a novel interactive learning paradigm with trials and demonstrations, showing its effectiveness in enhancing language acquisition in models from scratch.
Findings
Interactive feedback accelerates word learning.
Both trials and demonstrations are crucial for efficiency.
Teacher's word choices impact learning outcomes.
Abstract
Humans are efficient language learners and inherently social creatures. Our language development is largely shaped by our social interactions, for example, the demonstration and feedback from caregivers. Contrary to human language learning, recent advancements in large language models have primarily adopted a non-interactive training paradigm, and refined pre-trained models through feedback afterward. In this work, we explore how corrective feedback from interactions influences neural language acquisition from scratch through systematically controlled experiments, assessing whether it contributes to word learning efficiency in language models. We introduce a trial-and-demonstration (TnD) learning framework that incorporates three distinct components: student trials, teacher demonstrations, and a reward conditioned on language competence at various developmental stages. Our experiments…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsNatural Language Processing Techniques
