English

Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models

Computation and Language 2023-10-24 v2

Abstract

Large Language Models (LLMs) demonstrate remarkable performance on a variety of natural language understanding (NLU) tasks, primarily due to their in-context learning ability. This ability could be applied to building babylike models, i.e. models at small scales, improving training efficiency. In this paper, we propose a "CoThought" pipeline, which efficiently trains smaller "baby" language models (BabyLMs) by leveraging the Chain of Thought prompting of LLMs. Our pipeline restructures a dataset of less than 100M in size using GPT-3.5-turbo, transforming it into task-oriented, human-readable texts that are comparable to the school texts for language learners. The BabyLM is then pretrained on this restructured dataset in a RoBERTa fashion. In evaluations across 4 benchmarks, our BabyLM outperforms the vanilla RoBERTa in 10 linguistic, NLU, and question-answering tasks by more than 3 points, showing a superior ability to extract contextual information. These results suggest that compact LMs pretrained on small, LLM-restructured data can better understand tasks and achieve improved performance.

Keywords

Cite

@article{arxiv.2308.01684,
  title  = {Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models},
  author = {Zheyu Zhang and Han Yang and Bolei Ma and David Rügamer and Ercong Nie},
  journal= {arXiv preprint arXiv:2308.01684},
  year   = {2023}
}

Comments

CoNLL 2023 BabyLM Challenge

R2 v1 2026-06-28T11:47:14.538Z