English

Critical Thinking for Language Models

Computation and Language 2020-12-18 v2 Artificial Intelligence

Abstract

This paper takes a first step towards a critical thinking curriculum for neural auto-regressive language models. We introduce a synthetic corpus of deductively valid arguments, and generate artificial argumentative texts to train and evaluate GPT-2. Significant transfer learning effects can be observed: Training a model on three simple core schemes allows it to accurately complete conclusions of different, and more complex types of arguments, too. The language models generalize the core argument schemes in a correct way. Moreover, we obtain consistent and promising results for NLU benchmarks. In particular, pre-training on the argument schemes raises zero-shot accuracy on the GLUE diagnostics by up to 15 percentage points. The findings suggest that intermediary pre-training on texts that exemplify basic reasoning abilities (such as typically covered in critical thinking textbooks) might help language models to acquire a broad range of reasoning skills. The synthetic argumentative texts presented in this paper are a promising starting point for building such a "critical thinking curriculum for language models."

Keywords

Cite

@article{arxiv.2009.07185,
  title  = {Critical Thinking for Language Models},
  author = {Gregor Betz and Christian Voigt and Kyle Richardson},
  journal= {arXiv preprint arXiv:2009.07185},
  year   = {2020}
}
R2 v1 2026-06-23T18:33:46.374Z