Search papers, labs, and topics across Lattice.
Laboratoire Hubert Curien, UMR CNRS 5516, Saint-脡tienne, France
2
0
5
8
Fairness degradation in language models can silently escalate before performance metrics signal any issues, revealing a hidden danger in synthetic data training.
LLMs can achieve fairer outcomes through multi-agent negotiation than through individual ethical alignment, suggesting a path to fairness via interaction rather than monolithic design.
