To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining

• URL: http://arxiv.org/abs/2604.00715v1
• Date: Wed, 01 Apr 2026 10:26:03 GMT
• Title: To Memorize or to Retrieve: Scaling Laws for RAG-Considerate Pretraining
• Abstract summary: We study the trade-off between pretraining corpus size and retrieval store size across a wide range of model and data scales.<n>We find that retrieval consistently improves performance over parametric-only baselines across model scales.
• Score: 24.61808957290675
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. However, the relationship between parametric knowledge acquired during pretraining and non-parametric knowledge accessed via retrieval remains poorly understood, especially under fixed data budgets. In this work, we systematically study the trade-off between pretraining corpus size and retrieval store size across a wide range of model and data scales. We train OLMo-2-based LMs ranging from 30M to 3B parameters on up to 100B tokens of DCLM data, while varying both pretraining data scale (1-150x the number of parameters) and retrieval store size (1-20x), and evaluate performance across a diverse suite of benchmarks spanning reasoning, scientific QA, and open-domain QA. We find that retrieval consistently improves performance over parametric-only baselines across model scales and introduce a three-dimensional scaling framework that models performance as a function of model size, pretraining tokens, and retrieval corpus size. This scaling manifold enables us to estimate optimal allocations of a fixed data budget between pretraining and retrieval, revealing that the marginal utility of retrieval depends strongly on model scale, task type, and the degree of pretraining saturation. Our results provide a quantitative foundation for understanding when and how retrieval should complement pretraining, offering practical guidance for allocating data resources in the design of scalable language modeling systems.

Related papers

• Scaling Laws for Reranking in Information Retrieval [24.00475965133032]
  We present the first systematic study of scaling laws for rerankers.<n>Using a detailed case study with cross-encoder rerankers, we demonstrate that performance follows a predictable power law.<n>Our results establish scaling principles for reranking and provide actionable insights for building industrial-grade retrieval systems.
  arXiv  Detail & Related papers  (2026-03-05T05:03:07Z)
• Maximally-Informative Retrieval for State Space Model Generation [59.954191072042526]
  We introduce Retrieval In-Context Optimization (RICO) to minimize model uncertainty for a particular query at test-time.<n>Unlike traditional retrieval-augmented generation (RAG), which relies on externals for document retrieval, our approach leverages direct feedback from the model.<n>We show that standard top-$k$ retrieval with model gradients can approximate our optimization procedure, and provide connections to the leave-one-out loss.
  arXiv  Detail & Related papers  (2025-06-13T18:08:54Z)
• Exploring Training and Inference Scaling Laws in Generative Retrieval [50.82554729023865]
  Generative retrieval reformulates retrieval as an autoregressive generation task, where large language models generate target documents directly from a query.<n>We systematically investigate training and inference scaling laws in generative retrieval, exploring how model size, training data scale, and inference-time compute jointly influence performance.
  arXiv  Detail & Related papers  (2025-03-24T17:59:03Z)
• Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training [68.94373533768501]
  We model knowledge retention, the capacity of a pre-trained language model to memorize factual information from its corpus, and introduce a principled method to estimate it prior to training.<n>We propose Size-dependent Mutual Information (SMI), an information-theoretic predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering (QA) accuracy.
  arXiv  Detail & Related papers  (2025-02-06T13:23:53Z)
• Analyzing Similarity Metrics for Data Selection for Language Model Pretraining [39.02299450717135]
  Measuring similarity between training examples is critical for curating high-quality and diverse pretraining datasets for language models.<n>Standard off-the-shelf embedding models are not well-suited for the pretraining data curation setting.
  arXiv  Detail & Related papers  (2025-02-04T17:09:44Z)
• The interplay between domain specialization and model size [8.653321928148547]
  We investigate the interplay between domain and model size during continued pretraining under compute-constrained scenarios.<n>Our goal is to identify an optimal training regime for this scenario and detect patterns in this interplay that can be generalized across different model sizes and domains.
  arXiv  Detail & Related papers  (2025-01-03T19:28:53Z)
• What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
  We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy. By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
  arXiv  Detail & Related papers  (2024-11-12T09:52:40Z)
• Scaling Retrieval-Based Language Models with a Trillion-Token Datastore [85.4310806466002]
  We find that increasing the size of the datastore used by a retrieval-based LM monotonically improves language modeling and several downstream tasks without obvious saturation. By plotting compute-optimal scaling curves with varied datastore, model, and pretraining data sizes, we show that using larger datastores can significantly improve model performance for the same training compute budget.
  arXiv  Detail & Related papers  (2024-07-09T08:27:27Z)
• Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data [66.11139091362078]
  We provide the first model selection results on large pretrained Transformers from Huggingface using generalization metrics. Despite their niche status, we find that metrics derived from the heavy-tail (HT) perspective are particularly useful in NLP tasks.
  arXiv  Detail & Related papers  (2022-02-06T20:07:35Z)

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.