Masked Diffusion Language Models with Frequency-Informed Training
By: Despoina Kosmopoulou , Efthymios Georgiou , Vaggelis Dorovatas and more
Potential Business Impact:
Teaches computers language with less text.
We present a masked diffusion language modeling framework for data-efficient training for the BabyLM 2025 Challenge. Our approach applies diffusion training objectives to language modeling under strict data constraints, incorporating frequency-informed masking that prioritizes learning from rare tokens while maintaining theoretical validity. We explore multiple noise scheduling strategies, including two-mode approaches, and investigate different noise weighting schemes within the NELBO objective. We evaluate our method on the BabyLM benchmark suite, measuring linguistic competence, world knowledge, and human-likeness. Results show performance competitive to hybrid autoregressive-masked baselines, demonstrating that diffusion-based training offers a viable alternative for data-restricted language learning.
Similar Papers
Soft-Masked Diffusion Language Models
Machine Learning (CS)
Helps computers write better code, faster.
Mask and You Shall Receive: Optimizing Masked Language Modeling For Pretraining BabyLMs
Computation and Language
Teaches computers to understand words better.
Towards Data-Efficient Language Models: A Child-Inspired Approach to Language Learning
Computation and Language
Teaches computers to learn language like kids.