demographic-bias

Tag

Cards List
#demographic-bias

Effect of Demographic Bias on Skin Lesion Classification

arXiv cs.AI · yesterday Cached

This paper investigates the impact of demographic bias (sex and age) on skin lesion classification using ResNet models, finding that sex biases stem from data imbalances while age biases consistently favor younger groups, and evaluating multi-task and adversarial learning mitigation strategies.

0 favorites 0 likes
#demographic-bias

DART: Mitigating Harm Drift in Difference-Aware LLMs via Distill-Audit-Repair Training

arXiv cs.CL · 2026-04-21 Cached

DART (Distill-Audit-Repair Training) is a new training framework that addresses 'harm drift' in safety-aligned LLMs, where fine-tuning for demographic difference-awareness causes harmful content to appear in model explanations. On eight benchmarks, DART improves Llama-3-8B-Instruct accuracy from 39.0% to 68.8% while reducing harm drift cases by 72.6%.

0 favorites 0 likes
← Back to home

Submit Feedback