LIME: Making LLM Data More Efficient with Linguistic Metadata Embeddings
This addresses the challenge of data efficiency in large language model pre-training, offering a novel approach to leverage metadata for faster and more effective training.
The paper tackles the problem of inefficient pre-training for decoder-only language models by proposing LIME, a method that enriches token embeddings with linguistic metadata, resulting in up to 56% faster adaptation to training data and improved performance in language modeling and generative tasks.
Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential as a direct training signal remains under-explored. We challenge this status quo and propose LIME (Linguistic Metadata Embeddings), a method that enriches token embeddings with metadata capturing syntax, semantics, and contextual properties. LIME substantially improves pre-training efficiency. Specifically, it adapts up to 56% faster to the training data distribution, while introducing only 0.01% additional parameters at negligible compute overhead. Beyond efficiency, LIME improves tokenization, leading to remarkably stronger language modeling capabilities and generative task performance. These benefits persist across model scales (500M to 2B). In addition, we develop a variant with shifted metadata, LIME+1, that can guide token generation. Given prior metadata for the next token, LIME+1 improves reasoning performance by up to 38% and arithmetic accuracy by up to 35%.