# Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection Source: [Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:10:34.078Z Authors: Rajkumar Pujari, Erik Oveson, Priyanka Kulkarni, Elnaz Nouri Published: 2022-03-27T17:16:11.000Z ## Abstract As large Pre-trained Language Models (PLMs) trained on large amounts of data in an unsupervised manner become more ubiquitous, identifying various types of bias in the text has come into sharp focus. Existing "Stereotype Detection" datasets mainly adopt a diagnostic approach toward large PLMs. Blodgett et. al (2021a) show that there are significant reliability issues with the existing benchmark datasets. Annotating a reliable dataset requires a precise understanding of the subtle nuances of how stereotypes manifest in text. In this paper, we annotate a focused evaluation set for "Stereotype Detection" that addresses those pitfalls by de-constructing various ways in which stereotypes manifest in text. Further, we present a multi-task model that leverages the abundance of data-rich neighboring tasks such as hate speech detection, offensive language detection, misogyny detection, etc., to improve the empirical performance on "Stereotype Detection". We then propose a reinforcement-learning agent that guides the multi-task learning model by learning to identify the training examples from the neighboring tasks that help the target task the most. We show that the proposed models achieve significant empirical gains over existing baselines on all the tasks. ## 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. - [Coarse-Grained Stereotype Detection on Coarse-Grained Stereotype Detection (test)](): Coarse-Grained Stereotype Detection; Coarse-Grained Stereotype Detection (test); Macro F1: 74.18. - [Fine-Grained Stereotype Detection on Fine-Grained Stereotype Detection (test)](): Fine-Grained Stereotype Detection; Fine-Grained Stereotype Detection (test); Macro-F1: 67.94. - [Hate Speech Detection on Hate Speech Detection (test)](): Hate Speech Detection; Hate Speech Detection (test); Macro F1: 72.06. - [Misogyny Detection on Misogyny Detection (test)](): Misogyny Detection; Misogyny Detection (test); Macro-F1: 75.21. - [Offense Detection on Offense Detection (test)](): Offense Detection; Offense Detection (test); Macro F1: 0.6897. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()