activity
20242026
collaborators

5 papers

cs.LG2026

APEX: Probing Neural Networks via Activation Perturbation

Tao Ren, Xiaoyu Luo, Qiongxiu Li

Prior work on probing neural networks primarily relies on input-space analysis or parameter perturbation, both of which face fundamental limitations in accessing structural informa…

cs.CL2026

Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework

Xiaoyu Luo, Yiyi Chen, Qiongxiu Li +1

Large Language Models (LLMs) have been reported to "leak" Personally Identifiable Information (PII), with successful PII reconstruction often interpreted as evidence of memorizatio…

cs.CL2025

Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities

Xiaoyu Luo, Yiyi Chen, Johannes Bjerva +1

We present the first comprehensive study of Memorization in Multilingual Large Language Models (MLLMs), analyzing 95 languages using models across diverse model scales, architectur…

cs.LG2025

Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond

Qiongxiu Li, Xiaoyu Luo, Yiyi Chen +1

The role of memorization in machine learning (ML) has garnered significant attention, particularly as modern models are empirically observed to memorize fragments of training data.…

cs.LG2024

DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization

Xiaoyu Luo, Qiongxiu Li

Adversarial robustness, the ability of a model to withstand manipulated inputs that cause errors, is essential for ensuring the trustworthiness of machine learning models in real-w…