← Search

Reza Akbarian Bafghi

2 accepted papers

2025

Aligning to What? Limits to RLHF Based Alignment

NAACL 2025findings

Reinforcement Learning from Human Feedback (RLHF) is increasingly used to align large language models (LLMs) with human preferences. However, the effectiveness of RLHF in addressing underlying biases remains unclear. This study investigates the relationship between RLHF and both covert and overt bia…

2023

A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories

CVPR 2023poster

Our goal is to improve upon the status quo for designing image classification models trained in one domain that perform well on images from another domain. Complementing existing work in robustness testing, we introduce the first dataset for this purpose which comes from an authentic use case where…