FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Models

2023/02/10 by Viswanath, Hrishikesh, Zhang, Tianyi · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2302.05508

Abstract

Recent studies have demonstrated that large pretrained language models (LLMs) such as BERT and GPT-2 exhibit biases in token prediction, often inherited from the data distributions present in their training corpora. In response, a number of mathematical frameworks have been proposed to quantify, identify, and mitigate these the likelihood of biased token predictions. In this paper, we present a comprehensive survey of such techniques tailored towards widely used LLMs such as BERT, GPT-2, etc. We additionally introduce Fairpy, a modular and extensible toolkit that provides plug-and-play interfaces for integrating these mathematical tools, enabling users to evaluate both pretrained and custom language models. Fairpy supports the implementation of existing debiasing algorithms. The toolkit is open-source and publicly available at: \hrefhttps://github.com/HrishikeshVish/Fairpyhttps://github.com/HrishikeshVish/Fairpy

Cited by

• How AI Fails: An Interactive Pedagogical Tool for Demonstrating Dialectal Bias in Automated Toxicity Models

Related

• The Fair Language Model Paradox
• BEADs: Bias Evaluation Across Domains
• BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
• Identifying and Mitigating Social Bias Knowledge in Language Models
• Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing