Papers
arxiv:2502.05551

FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy

Published on May 31, 2025
Authors:
,
,
,
,
,
,
,

Abstract

A four-quadrant multi-stage pretraining strategy partitions data by perplexity and perplexity difference to improve large language model performance on MMLU and CMMLU.

Large language models (LLMs) have significantly advanced human language understanding and generation, with pretraining data quality and organization being crucial to their performance. Multi-stage pretraining is a promising approach, but existing methods often lack quantitative criteria for data partitioning and instead rely on intuitive heuristics. In this paper, we propose the novel Four-quadRAnt Multi-stage prEtraining strategy (FRAME), guided by the established principle of organizing the pretraining process into four stages to achieve significant loss reductions four times. This principle is grounded in two key findings: first, training on high Perplexity (PPL) data followed by low PPL data, and second, training on low PPL difference (PD) data followed by high PD data, both causing the loss to drop significantly twice and performance enhancements. By partitioning data into four quadrants and strategically organizing them, FRAME achieves a remarkable 16.8% average improvement over random across MMLU and CMMLU for the 3B model, effectively boosting LLM performance.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2502.05551
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2502.05551 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2502.05551 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2502.05551 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.