cs.CLSep 9, 2026

Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling

Authors: Tingshuo Fan, Hongtao Mu, Tianyu Zhou, Hansen Liu, Tao Ji

Abstract

When training data are limited, increasing parameter count is not the only way to improve language-model performance. A small parameter set, when repeatedly applied, can also deliver comparable performance. We study Looped GPT-BERT in the BabyLM 2026 Strict-small setting, combining GPT-BERT's masked next-token and causal language-modeling objectives with depth-wise parameter sharing. We train on a preprocessed 7.48M-word English corpus and compare objective ratios, non-looped and looped architectures, and loop counts. Our final 4×124\times12 model uses four physical layers for twelve recurrent traversals and contains 12.18M parameters. The BabyLM 2026 leaderboard reports an Overall Average of 35.42 and an NLP Average of 48.48. Compared with public BabyLM 10M Strict-small GPT-2 and GPT-BERT baselines, it achieves comparable performance on selected linguistic and downstream metrics, including BLiMP and GLUE, with fewer parameters. The loop ablations show that additional recurrent computation can improve training and preserve strong performance on selected linguistic tasks, whereas poorer performance on other tasks may reveal an inherent limitation of the looped design: using only a few physical layers restricts the model's representational space.

Explore similar work

CardsList
  1. CHASE: Cache-Hole-Adapted Skip Exit for Looped State-Space Language Models

    Jul 11, 2026Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo +1Recurrence

  2. The Wiola Architecture for Efficient Small Language Models

    Jul 1, 2026Aryuemaan Kumar Chowdhury, Afreen Shaik, Yaparla Bhargavi +1Small Language ModelsRotary Position Embedding