all InfoSec news
Evaluating and Mitigating Linguistic Discrimination in Large Language Models
April 30, 2024, 4:11 a.m. | Guoliang Dong, Haoyu Wang, Jun Sun, Xinyu Wang
cs.CR updates on arXiv.org arxiv.org
Abstract: By training on text in various languages, large language models (LLMs) typically possess multilingual support and demonstrate remarkable capabilities in solving tasks described in different languages. However, LLMs can exhibit linguistic discrimination due to the uneven distribution of training data across languages. That is, LLMs are hard to keep the consistency of responses when faced with the same task but depicted in different languages.
In this study, we first explore the consistency in the LLMs' …
arxiv can capabilities cs.ai cs.cl cs.cr cs.se data discrimination distribution language language models languages large linguistic llms support text training training data
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Sr. Product Manager
@ MixMode | Remote, US
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Product Security Engineer
@ ServiceNow | Hyderabad, India
Senior Application Security Engineer (Puerto Rico)
@ RTX | HPR99: Field Office – PR, Remote Location, Remote City, PR, 00921 USA