Debiasing Static Embeddings' Impact on Fairness-Accuracy Trade-off in Contextualized Models

Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can learn, perpetuate, and amplify harmful social biases. In this paper, we present a comprehensive survey of bias evaluation and mitigation techniques for LLMs. We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing, defining distinct facets of harm and introducing several desiderata to operationalize fair

Research goal: What is the impact of debiasing methods derived from static embeddings on the fairness-accuracy trade-off in contextualized models evaluated on the BiasBios dataset?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.2/10.