Dongrui Liu

The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models

2025

Ensuring awareness of fairness and privacy in Large Language Models (LLMs) is critical.Interestingly, we discover a counterintuitive trade-off phenomenon that enhancing an LLM's privacy awareness through Supervised Fine-Tuning (SFT) methods significantly decreases its fairness awareness …