Tag: AI language models
Browse our exclusive articles!
Open-Ended Arabic QA Benchmark with Dialect Variants
Explore a new Arabic QA benchmark testing dialects and open-ended questions to improve LLMs' cultural and linguistic understanding.
STELA: Linguistics-Based Watermarking for LLMs
Discover STELA, a linguistics-aware watermarking method for LLMs that ensures robust, publicly verifiable AI content detection without model access.
DASB: Benchmark for Discrete Audio and Speech Tokens
Explore DASB, a comprehensive benchmark for evaluating discrete audio and speech tokens across diverse tasks in audio and language processing.
Prevent Unauthorized Distillation of Language Models
Learn how trace rewriting protects large language models from unauthorized knowledge distillation while embedding verifiable watermarks.
Uniform Information Density in LLM Reasoning: New Insights
Explore how uniform information density affects reasoning quality in large language models using entropy-based metrics across seven benchmarks.