Trishna Ugale

CARP: Constraint-Aware Re-Prompting for Zero-Shot Bias Mitigation in Compact LLMs

Small language models between 125M and 1.6B parameters are being widely used similar to large models: phones, tablets, classroom apps, and small lab prototypes. But these models still carry the biases during pretraining, and the usual fixes like fine-tuning or RLHF are too heavy for the same environments where these mo...