3 citations · 5 across the 15 of their papers we have counts for
8 papers · 1 filter
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…
LAGO: Few-shot Crosslingual Embedding Inversion Attacks via Language Similarity-Aware Graph Optimization
Wenrui Yu, Yiyi Chen, Johannes Bjerva +2
We propose LAGO - Language Similarity-Aware Graph Optimization - a novel approach for few-shot cross-lingual embedding inversion attacks, addressing critical privacy vulnerabilitie…
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…
NLP Security and Ethics, in the Wild
Heather Lent, Erick Galinkin, Yiyi Chen +3
As NLP models are used by a growing number of end-users, an area of increasing importance is NLP Security (NLPSec): assessing the vulnerability of models to malicious attacks and d…
Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis
Yiyi Chen, Qiongxiu Li, Russa Biswas +1
Language Confusion is a phenomenon where Large Language Models (LLMs) generate text that is neither in the desired language, nor in a contextually appropriate language. This phenom…
Patterns of Persistence and Diffusibility across the World's Languages
Yiyi Chen, Johannes Bjerva
Language similarities can be caused by genetic relatedness, areal contact, universality, or chance. Colexification, i.e. a type of similarity where a single lexical form is used to…
Patterns of Closeness and Abstractness in Colexifications: The Case of Indigenous Languages in the Americas
Yiyi Chen, Johannes Bjerva
Colexification refers to linguistic phenomena where multiple concepts (meanings) are expressed by the same lexical form, such as polysemy or homophony. Colexifications have been fo…
CreoleVal: Multilingual Multitask Benchmarks for Creoles
Heather Lent, Kushal Tatariya, Raj Dabre +18
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.While the genealogical ties between Creoles and a number of h…