Emilio M Serrano

When Fairness Metrics Fail: Auditing Collapse and Transfer Risks in LLM Decision Systems

Code and experimental outputs accompanying the paper When Fairness Metrics Fail: Auditing Collapse and Transfer Risks in LLM Decision Systems. The study audits fairness evaluation practice in tabular classification with Large Language Models under in-context learning, using thirteen data-level and prompt-level interven...