Spanish

The 'Spanish' dataset/benchmark contains data used to evaluate the performance of multilingual large language models (LLMs) in generating and assessing text, particularly in the context of low-resource language scenarios.

Papers using Spanish (4)

Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study2026Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights2026Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection2026Multilingual Definition Modeling2025