Towards Understanding and Mitigating Social Biases in Language Models

Abstract

As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes. Among such real-world deployments are large-scale pretrained language models (LMs) that can be potentially dangerous in manifesting undesirable representational biases - harmful biases resulting from stereotyping that propagate negative generalizations involving gender, race, religion, and other social constructs. As a step towards improving the fairness of LMs, we carefully define several sources of representational biases before proposing new benchmarks and metrics to measure them. With these tools, we propose steps towards mitigating social biases during text generation. Our empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information for high-fidelity text generation, thereby pushing forward the performance-fairness Pareto frontier.

ICML 2021, code available at https://github.com/pliang279/LM_bias

Cited by in corpus (4)

• AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing
• Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
• Using ChatGPT in HCI Research -- A Trioethnography
• AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models