TechRxiv survey proposes philosophical taxonomy of bias in large language models

[TechRxiv] A TechRxiv preprint survey by Kai Jiang and co-authors introduces a philosophical taxonomy that reframes bias in large language models, organizing existing work around three core areas: bias evaluation, bias mitigation, and evaluation of mitigation techniques. The survey distinguishes substantial harms — tangible, adverse impacts on individuals or groups — from representational harms, described as demeaning or stereotyping portrayals that violate dignity, and it highlights how these harms often interact and reinforce one another. According to the authors, structuring metrics, datasets and methods within this taxonomy provides a foundation for developing fairer and more inclusive language models. The paper is a preprint and has not been peer reviewed.