arXiv:2407.10853v4 Announce Type: replace-cross
Abstract: Bias and fairness risks in Large Language Models (LLMs) vary substantially across deployment contexts, yet existing approaches lack systematic guidance for selecting appropriate evaluation metrics. We present a decision framework that maps LLM use cases, characterized by a model and population of prompts, to relevant bias and fairness metrics based on task type, whether prompts contain protected attribute mentions, and stakeholder priorities. Our framework addresses toxicity, stereotyping, counterfactual unfairness, and allocational harms, and introduces novel metrics based on stereotype classifiers and counterfactual adaptations of text similarity measures. All metrics require only LLM outputs for computation, simplifying implementation while avoiding embedding-based approaches that often correlate poorly with downstream harms. We provide an open-source Python library, LangFair, for practical adoption. Extensive experiments demonstrate that fairness risks cannot be reliably assessed from benchmark performance alone: results on one prompt dataset likely overstate or understate risks for another, underscoring that fairness evaluation must be grounded in the specific deployment context.
