3 papers
cs.LG2026
Estimating the expected output of wide random MLPs more efficiently than sampling
Wilson Wu, Victor Lecomte, Michael Winer +3
By far the most common way to estimate an expected loss in machine learning is to draw samples, compute the loss on each one, and take the empirical average. However, sampling is n…
cs.CL2025
DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture
Arijit Maji, Raghvendra Kumar, Akash Ghosh +6
We introduce DRISHTIKON, a first-of-its-kind multimodal and multilingual benchmark centered exclusively on Indian culture, designed to evaluate the cultural understanding of genera…
cs.CL2024
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal +2
Contrastive decoding (CD) (Li et al., 2023) improves the next-token distribution of a large expert language model (LM) using a small amateur LM. Although CD is applied to various L…