Dbias: Detecting biases and ensuring Fairness in news articles

Abstract

The problem of fairness is garnering a lot of interest in the academic and broader literature due to the increasing use of data-centric systems and algorithms in machine learning. This paper introduces Dbias (https://pypi.org/project/Dbias/), an open-source Python package for ensuring fairness in news articles. Dbias can take any text to determine if it is biased. Then, it detects biased words in the text, masks them, and suggests a set of sentences with new words that are bias-free or at least less biased. We conduct extensive experiments to assess the performance of Dbias. To see how well our approach works, we compare it to the existing fairness models. We also test the individual components of Dbias to see how effective they were. The experimental results show that Dbias outperforms all the baselines in terms of accuracy and fairness. We make this package (Dbias) as publicly available for the developers and practitioners to mitigate biases in textual data (such as news articles), as well as to encourage extension of this work.

Benchmarking the Ethics of Large Language Models with Polarizing Topics

“…Analyzing the impact of these biases on the outputs generated by LLMs highlighted the potential for reinforcement of harmful stereotypes, emphasizing the need for continuous monitoring and improvement [6]. Sentiment analysis techniques were applied to detect and quantify biases in model responses, providing a quantifiable measure of bias presence [7,8]. Frameworks for bias detection were refined, incorporating advanced metrics that allowed for a more nuanced understanding of bias manifestations in LLMs [9].…”