This work develops a policy gradient technique involving a group-level reward function that operates on matched pairs of counterfactual prompts that reduces counterfactual differences while preserving overall response quality and proves that the models continue to adapt appropriately when such sensitive information is...
Başar Demir, Emma Shen, Ksheeraj Sai Vepuri et al.· 0 citations
This work proposes a general RL-based framework for Distribution Matching allowing matching the distribution of a latent categorical attribute of model outputs to a specified target distribution and proposes reward functions for other divergences such as KL and Jensen-Shannon and motivate them with theoretical justific...
Sourabh Kulkarni, Ksheeraj Sai Vepuri, B. Demir et al.· 1 citation
This paper shows that Vision-Language Models (VLMs) can internally distinguish when abstention is required, but fail to express it anyway, and introduces Penalized Epistemic Calibration Score (PECS), a new robust metric that requires models to both answer correctly when the outcome is knowable, and abstain when the out...
Fnu Pramono, J. Cai, Sourabh Kulkarni· 5 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.