Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay

• URL: http://arxiv.org/abs/2605.26097v1
• Date: Mon, 25 May 2026 17:54:34 GMT
• Title: Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
• Abstract summary: We show that self-generated samples serve as effective replay data, nearly eliminating forgetting.<n>We find that forgetting persists when the model has little remaining capacity.
• Score: 44.18996691373878
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast, language models can sample from their own training distribution, and we show that these self-generated samples serve as effective replay data, nearly eliminating forgetting. We find that forgetting nonetheless persists when the model has little remaining capacity: models pretrained close to saturation cannot absorb new information without overwriting prior knowledge. When capacity is not the limiting factor, low learning rates reduce forgetting but require substantially more training steps. Replay breaks this tradeoff, enabling fast, high-learning-rate finetuning without forgetting.

Related papers

• Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning [30.941068379610794]
  We study the behavior of large-scale pretrained Vision-Language-Action (VLA) models trained from scratch.<n>We find that pretrained VLAs are remarkably resistant to forgetting compared with smaller policy models trained from scratch.<n>Our analysis reveals that pretraining plays a critical role in downstream continual learning performance.
  arXiv  Detail & Related papers  (2026-03-04T08:03:13Z)
• Continual Learning via Sparse Memory Finetuning [58.163704181154834]
  We investigate whether sparse parameter updates can enable learning without catastrophic forgetting.<n>By updating only the memory slots that are highly activated by a new piece of knowledge relative to usage on pretraining data, we reduce interference between new knowledge and the model's existing capabilities.<n>We find that sparse memory finetuning learns new knowledge while exhibiting substantially less forgetting.
  arXiv  Detail & Related papers  (2025-10-16T19:44:38Z)
• From Acceleration to Saturation: Scaling Behavior of Bootstrapped Language Model Pretraining [2.569647910019739]
  We study the scaling behavior of bootstrapped pretraining and find that its scaling efficiency diminishes in a predictable manner.<n>Our findings provide practical insights for efficient language model training and raise important considerations for the reuse of overtrained models.
  arXiv  Detail & Related papers  (2025-10-08T00:59:33Z)
• Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models [19.136589266017694]
  Training large language models typically involves pre-training on massive corpora.<n>New data often causes distribution shifts, leading to performance degradation on previously learned tasks.<n>We take a deeper look at two popular proposals for addressing this distribution shift: experience replay and gradient alignment.
  arXiv  Detail & Related papers  (2025-08-03T20:07:15Z)
• AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling [53.54623137152208]
  We introduce AutoElicit to extract knowledge from large language models and construct priors for predictive models.<n>We show these priors are informative and can be refined using natural language.<n>We find that AutoElicit yields priors that can substantially reduce error over uninformative priors, using fewer labels, and consistently outperform in-context learning.
  arXiv  Detail & Related papers  (2024-11-26T10:13:39Z)
• Controlling Forgetting with Test-Time Data in Continual Learning [15.455400390299593]
  Ongoing Continual Learning research provides techniques to overcome catastrophic forgetting of previous information when new knowledge is acquired. We argue that test-time data hold great information that can be leveraged in a self supervised manner to refresh the model's memory of previous learned tasks.
  arXiv  Detail & Related papers  (2024-06-19T15:56:21Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Embedding Recycling for Language Models [38.11465250435789]
  We study how to decrease computational cost in such settings through embedding recycling (ER) We propose caching an intermediate layer's output from a pretrained model and finetuning the remaining layers for new tasks. We show that our method provides a 100% speedup during training and a 55-86% speedup for inference, and has negligible impacts on accuracy for text classification and entity recognition tasks in the scientific domain.
  arXiv  Detail & Related papers  (2022-07-11T16:36:14Z)
• BERT WEAVER: Using WEight AVERaging to enable lifelong learning for transformer-based models in biomedical semantic search engines [49.75878234192369]
  We present WEAVER, a simple, yet efficient post-processing method that infuses old knowledge into the new model. We show that applying WEAVER in a sequential manner results in similar word embedding distributions as doing a combined training on all data at once.
  arXiv  Detail & Related papers  (2022-02-21T10:34:41Z)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)
• Dynamic Model Pruning with Feedback [64.019079257231]
  We propose a novel model compression method that generates a sparse trained model without additional overhead. We evaluate our method on CIFAR-10 and ImageNet, and show that the obtained sparse models can reach the state-of-the-art performance of dense models.
  arXiv  Detail & Related papers  (2020-06-12T15:07:08Z)

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.