# PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning Source: [PRBoost: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:12:15.413Z Authors: Rongzhi Zhang, Yue Yu, Pranav Shetty, Le Song, Chao Zhang Published: 2022-03-18T04:23:20.000Z ## Abstract Weakly-supervised learning (WSL) has shown promising results in addressing label scarcity on many NLP tasks, but manually designing a comprehensive, high-quality labeling rule set is tedious and difficult. We study interactive weakly-supervised learning -- the problem of iteratively and automatically discovering novel labeling rules from data to improve the WSL model. Our proposed model, named PRBoost, achieves this goal via iterative prompt-based rule discovery and model boosting. It uses boosting to identify large-error instances and then discovers candidate rules from them by prompting pre-trained LMs with rule templates. The candidate rules are judged by human experts, and the accepted rules are used to generate complementary weak labels and strengthen the current model. Experiments on four tasks show PRBoost outperforms state-of-the-art WSL baselines up to 7.1% and bridges the gaps with fully supervised models. Our Implementation is available at \\url{https://github.com/rz-zhang/PRBoost}. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Relation Extraction on TACRED v1.0 (test)](): Relation Extraction; TACRED v1.0 (test); F1 Score: 48.1. - [Text Classification on AG News (test)](): Text Classification; AG News (test); Accuracy: 88.9. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()