Papers
arxiv:2505.19893

ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining

Published on May 26
Authors:
,

Abstract

Efficient Selective Language Modeling improves large language model pretraining by selectively retaining informative tokens, reducing computational cost while maintaining or enhancing performance.

AI-generated summary

Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency. We introduce Efficient Selective Language Modeling (ESLM), a risk-aware algorithm that improves training efficiency and distributional robustness by performing online token-level batch selection. ESLM leverages per-token statistics (e.g., entropy or loss) and applies value-at-risk thresholding to retain only the most informative tokens per batch. This data-centric mechanism reshapes the training loss, prioritizing high-risk tokens and eliminating redundant gradient computation. We frame ESLM as a bilevel game: the model competes with a masking adversary that selects worst-case token subsets under a constrained thresholding rule. In the loss-based setting, ESLM recovers conditional value-at-risk loss minimization, providing a principled connection to distributionally robust optimization. We extend our approach to Ada-ESLM, which adaptively tunes the selection confidence during training. Experiments on GPT-2 pretraining show that ESLM significantly reduces training FLOPs while maintaining or improving both perplexity and downstream performance compared to baselines. Our approach also scales across model sizes, pretraining corpora, and integrates naturally with knowledge distillation.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2505.19893 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/2505.19893 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/2505.19893 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.