LMPriors: Pre-Trained Language Models as Task-Specific Priors

Choi, Kristy, Cundy, Chris, Srivastava, Sanjari, Ermon, Stefano

arXiv.org Artificial Intelligence 

Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors. This is to encourage them to learn in ways that are compatible with our understanding of the world. But in contrast to generic priors such as shrinkage or sparsity, we draw inspiration from the recent successes of large-scale language models (LMs) to construct task-specific priors distilled from the rich knowledge of LMs. Our method, Language Model Priors (LMPriors), incorporates auxiliary natural language metadata about the task -- such as variable names and descriptions -- to encourage downstream model outputs to be consistent with the LM's common-sense reasoning based on the metadata. Empirically, we demonstrate that LMPriors improve model performance in settings where such natural language descriptions are available, and perform well on several tasks that benefit from such prior knowledge, such as feature selection, causal inference, and safe reinforcement learning.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found