Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

• URL: http://arxiv.org/abs/2511.07384v1
• Date: Mon, 10 Nov 2025 18:43:07 GMT
• Title: Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
• Authors: Sean McLeish, Ang Li, John Kirchenbauer, Dayal Singh Kalra, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Jonas Geiping, Tom Goldstein, Micah Goldblum,
• Abstract summary: We study how to convert existing pretrained non-recurrent language models into depth-recurrent models.<n>We find that using a curriculum of recurrences to increase the effective depth of the model over the course of training preserves performance while reducing total computational cost.
• Score: 113.48450265178953
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in depth-recurrent language models show that recurrence can decouple train-time compute and parameter count from test-time compute. In this work, we study how to convert existing pretrained non-recurrent language models into depth-recurrent models. We find that using a curriculum of recurrences to increase the effective depth of the model over the course of training preserves performance while reducing total computational cost. In our experiments, on mathematics, we observe that converting pretrained models to recurrent ones results in better performance at a given compute budget than simply post-training the original non-recurrent language model.

Related papers

• Loop Neural Networks for Parameter Sharing [1.1049608786515839]
  We introduce a novel Loop Neural Network, which achieves better performance by utilizing longer computational time without increasing the model size. Our approach revisits the input multiple times, refining the prediction by iteratively looping over a subset of the model with residual connections. We demonstrate the effectiveness of this method through experiments comparing versions of GPT-2 with our loop models, showing improved performance in language modeling tasks while maintaining similar parameter counts.
  arXiv  Detail & Related papers  (2024-09-21T17:07:42Z)
• Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models [29.367678364485794]
  We show how to design efficacious data distributions and learning rate schedules for continued pretraining of language models. We show an improvement of 9% in average model accuracy compared to the baseline of continued training on the pretraining set.
  arXiv  Detail & Related papers  (2024-07-09T22:37:59Z)
• Training Trajectories of Language Models Across Scales [99.38721327771208]
  Scaling up language models has led to unprecedented performance gains. How do language models of different sizes learn during pre-training? Why do larger language models demonstrate more desirable behaviors?
  arXiv  Detail & Related papers  (2022-12-19T19:16:29Z)
• Logarithmic Continual Learning [11.367079056418957]
  We introduce a neural network architecture that logarithmically reduces the number of self-rehearsal steps in the generative rehearsal of continually learned models. In continual learning (CL), training samples come in subsequent tasks, and the trained model can access only a single task at a time.
  arXiv  Detail & Related papers  (2022-01-17T17:29:16Z)
• Improving Non-autoregressive Generation with Mixup Training [51.61038444990301]
  We present a non-autoregressive generation model based on pre-trained transformer models. We propose a simple and effective iterative training method called MIx Source and pseudo Target. Our experiments on three generation benchmarks including question generation, summarization and paraphrase generation, show that the proposed framework achieves the new state-of-the-art results.
  arXiv  Detail & Related papers  (2021-10-21T13:04:21Z)
• bert2BERT: Towards Reusable Pretrained Language Models [51.078081486422896]
  We propose bert2BERT, which can effectively transfer the knowledge of an existing smaller pre-trained model to a large model. bert2BERT saves about 45% and 47% computational cost of pre-training BERT_BASE and GPT_BASE by reusing the models of almost their half sizes.
  arXiv  Detail & Related papers  (2021-10-14T04:05:25Z)
• Maximizing Efficiency of Language Model Pre-training for Learning Representation [6.518508607788086]
  ELECTRA is a novel approach for improving the compute efficiency of pre-trained language models. Our work proposes adaptive early exit strategy to maximize the efficiency of the pre-training process.
  arXiv  Detail & Related papers  (2021-10-13T10:25:06Z)
• Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimates [52.164757178369804]
  Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget. We conduct an empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework. We also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance.
  arXiv  Detail & Related papers  (2021-01-20T13:59:25Z)
• Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning [74.25168207651376]
  Fine-tuning pre-trained language models to downstream cross-lingual tasks has shown promising results. We leverage continual learning to preserve the cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. Our methods achieve better performance than other fine-tuning baselines on the zero-shot cross-lingual part-of-speech tagging and named entity recognition tasks.
  arXiv  Detail & Related papers  (2020-04-29T14:07:18Z)
• PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models [9.496524884855559]
  This paper presents an efficient provenance-based approach, PrIU, for incrementally updating model parameters without sacrificing prediction accuracy. We prove the correctness and convergence of the incrementally updated model parameters, and validate it experimentally. Experimental results show that up to two orders of magnitude speed-ups can be achieved by PrIU-opt compared to simply retraining the model from scratch, yet obtaining highly similar models.
  arXiv  Detail & Related papers  (2020-02-26T21:04:06Z)

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.