Top-K masking schemes have been proposed as a method to promote sparse representations in Information Retrieval (IR) tasks, as a simple alternative to Floating Point Operations per Second (FLOPS) regularization. Algorithms such as Bilingual Lexical and Document Expansion Model (BLADE), adopt this approach as a post-processing stage. We propose using Top-P Dynamic Masking similar to Nucleus Sampling in Large Language Models, and demonstrate better performance than Top-K masking. Specifically, we evaluate our methods in the domain of Cross Language Information Retrieval (CLIR)
@article{arxiv.2510.19758,
title = {Top-P Masking for Cross Language Information Retrieval},
author = {Joseph Casale and Andrew Silverschotz and Joseph DeSimone},
journal= {arXiv preprint arXiv:2510.19758},
year = {2025}
}