3 papers
cs.CL2025
EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences
Kshitish Ghate, Andy Liu, Devansh Jain +5
As large language models (LLMs) are deployed globally, creating pluralistic systems that can accommodate the diverse preferences and values of users worldwide becomes essential. We…
cs.AI2025
Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders
Kshitish Ghate, Isaac Slaughter, Kyra Wilson +2
While recent work has found that vision-language models trained under the Contrastive Language Image Pre-training (CLIP) framework contain intrinsic social biases, the extent to wh…
cs.CL2025
Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes
Kshitish Ghate, Tessa Charlesworth, Mona Diab +1
To build fair AI systems we need to understand how social-group biases intrinsic to foundational encoder-based vision-language models (VLMs) manifest in biases in downstream tasks.…