Research
Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks
arXiv:2601.03448v2 Announce Type: replace Abstract: Language models (LMs) are pre-trained on raw text datasets to generate text sequences token-by-token. While this approach facilitates the learning o
arXiv:2601.03448v2 Announce Type: replace Abstract: Language models (LMs) are pre-trained on raw text datasets to generate text sequences token-by-token. While this approach facilitates the learning of world knowledge and reasoning, it does not explicitly optimize for linguistic competence. To bridge this gap, we propose L2T, a pre-training framework integrating Language Learning Tasks alongside standard next-token prediction. Inspired by human language acquisition, L2T transforms raw text into structured input-output pairs to provide explicit linguistic stimulation. Pre-training LMs on a mixture of raw text and L2T data not only improves overall performance on linguistic competence benchmarks but accelerates its acquisition, while maintaining competitive performance on general reasoning tasks.
Related
- Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight
- Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
- Efficient PRM Training Data Synthesis via Formal Verification
- Just Pass Twice: Efficient Token Classification with LLMs for Zero-Shot NER
Source: arXiv cs.CL | 2026-04-17