SOURCE-LINKED INTELLIGENCE

Task-Level Natural Language Priors as Learning Signals for Low-Resource LLM Training

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Large language models (LLMs) often struggle when low-resource training data are ambiguous or incomplete. Task-level natural-language priors can provide useful guidance in such settings, but existing approaches usually treat these priors as input context rather than as learning signals during training. We propose Prior-Guided Tuning (PGT), a training perspective that incorporates natural-language priors as auxiliary learning signals for low-resource LLM training. Under this perspective, we introduce Contrastive Prior Steering (CPS), which keeps the original supervised objective intact while add

Read original source ↗ Open in workspace

recordType

paper

region

Global