Xu-Peng Zhang

CausalFairAudit: Tamper-Evident Auditing for LLM Fairness Repair

Large language models (LLM) are increasingly used to support educational risk prediction, but their decisions may encode sensitive-attribute bias and are difficult to audit after deployment. Prompt-based fairness repair can change model behavior, yet it usually does not record which causal pathways were repaired or whe...