39 citations · 49 across the 9 of their papers we have counts for
5 papers · 1 filter
ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground Truth
Salman Rahman, Sruthi Gorantla, Arpit Gupta +3
Training process reward models (PRMs) requires step-level correctness labels, obtained either through expensive human annotation or by relying on ground-truth answers, limiting the…
Fair Active Ranking from Pairwise Preferences
Sruthi Gorantla, Sara Ahmadian
We investigate the problem of probably approximately correct and fair (PACF) ranking of items by adaptively evoking pairwise comparisons. Given a set of items that belong to di…
Optimizing Group-Fair Plackett-Luce Ranking Models for Relevance and Ex-Post Fairness
Sruthi Gorantla, Eshaan Bhansali, Amit Deshpande +1
In learning-to-rank (LTR), optimizing only the relevance (or the expected ranking utility) can cause representational harm to certain categories of items. Moreover, if there is imp…
Socially Fair Center-based and Linear Subspace Clustering
Sruthi Gorantla, Kishen N. Gowda, Amit Deshpande +1
Center-based clustering (e.g., -means, -medians) and clustering using linear subspaces are two most popular techniques to partition real-world data into smaller clusters. How…
Sampling Ex-Post Group-Fair Rankings
Sruthi Gorantla, Amit Deshpande, Anand Louis
Randomized rankings have been of recent interest to achieve ex-ante fairer exposure and better robustness than deterministic rankings. We propose a set of natural axioms for random…