Tag
The study reveals that thinking in reasoning language models has an asymmetric dual effect on counterfactual fairness: it resolves some biases but creates more, with the latter outnumbering the former by about 5× across models and datasets.
This paper theoretically and empirically studies the relationship between counterfactual fairness (CF) and group fairness (GF) in image classification, introducing new CF evaluation datasets (CelebA-CF and LFW-CF). It finds that CF does not imply GF in images due to latent attributes correlated with sensitive attributes, and proposes Counterfactual Knowledge Distillation (CKD) to mitigate this.
This research paper finds that language models exhibit increased dialect bias when comparing Standard American English and African-American Vernacular English side-by-side, even after safety fine-tuning. Counterfactual fairness fine-tuning can reduce some biases in isolation but not consistently in contrastive settings.