CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring the (Lack of) Cultural Knowledge of LLMs Paper • 2410.02677 • Published Oct 3, 2024
StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements Paper • 2408.15666 • Published Aug 28, 2024 • 11
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data? Paper • 2407.16607 • Published Jul 23, 2024 • 23
How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions Paper • 2406.14805 • Published Jun 21, 2024 • 3
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing Paper • 2406.08464 • Published Jun 12, 2024 • 67
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs Paper • 2402.11753 • Published Feb 19, 2024 • 6
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding Paper • 2402.08983 • Published Feb 14, 2024 • 4