Decomposed Trust: Privacy, Adversarial Robustness, Ethics, and Fairness in Low-Rank LLMs

ArXi:2511.22099v3 Announce Type: replace-cross Large language models (LLMs) have driven major advances across domains, yet their massive size hinders deployment in resource-constrained settings. Low-rank factorization addresses this challenge by compressing models to effectively reduce their computation and memory consumption while maintaining accuracy. While these compressed models boast benign performance and system-level advantages, their trustworthiness implications remain poorly understood.