Multilinguality

Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis
Language Confusion is a phenomenon where Large Language Models (LLMs) generate text that is neither in the desired language, nor in a …
PDF Cite Code
Leveraging Adapters for Improved Cross-lingual Transfer for Low-Resource Creole MT
Creole languages are low-resource languages, often genetically related to languages like English, French, and Portuguese, due to their …
PDF Cite
CreoleVal: Multilingual Multitask Benchmarks for Creoles
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research. While the …
PDF Cite Code
Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks
Large Language Models (LLMs) are susceptible to malicious influence by cyber attackers through intrusions such as adversarial, …
PDF Cite
Text Embedding Inversion Security for Multilingual Language Models
Textual data is often represented as real-numbered embeddings in NLP, particularly with the popularity of large language models (LLMs) …
PDF Cite Code
Patterns of Persistence and Diffusibility across World's Languages
Language similarities can be caused by genetic relatedness, areal contact, universality, or chance. Colexification, i.e. a type of …
PDF Cite
Typological Challenges for the Application of Multilingual Language Models in the Digital Humanities
This chapter explores the challenges faced by multilingual digital humanities (DH) researchers when using natural language processing …
PDF Cite