Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
Dasol Choi, Eugenia Kim, Jaewon Noh +14
Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's a…
cs.CL2024
Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships
Myung Gyo Oh, Hong Eun Ahn, Leo Hyun Park +1
Neural language models (LMs) are vulnerable to training data extraction attacks due to data memorization. This paper introduces a novel attack scenario wherein an attacker adversar…