3 citations · 4 across the 6 of their papers we have counts for
5 papers · 1 filter
When Can Proxies Improve the Sample Complexity of Preference Learning?
Yuchen Zhu, Daniel Augusto de Souza, Zhengyan Shi +4
We address the problem of reward hacking, where maximising a proxy reward does not necessarily increase the true reward. This is a key concern for Large Language Models (LLMs), as…
Mind the Graph When Balancing Data for Fairness or Robustness
Jessica Schrouff, Alexis Bellot, Amal Rannen-Triki +5
Failures of fairness or robustness in machine learning predictive settings can be due to undesired dependencies between covariates, outcomes and auxiliary factors of variation. A c…
Proxy Methods for Domain Adaptation
Katherine Tsai, Stephen R. Pfohl, Olawale Salaudeen +5
We study the problem of domain adaptation under distribution shift, where the shift is due to a change in the distribution of an unobserved, latent variable that confounds both the…
CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
Ibrahim Alabdulmohsin, Xiao Wang, Andreas Steiner +3
We study the effectiveness of data-balancing for mitigating biases in contrastive language-image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffir…
Predictive Churn with the Set of Good Models
Jamelle Watson-Daniels, Flavio du Pin Calmon, Alexander D'Amour +3
Issues can arise when research focused on fairness, transparency, or safety is conducted separately from research driven by practical deployment concerns and vice versa. This separ…