Flores-200
Emerging7papers using it
2024first seen
The 'FLORES-200' dataset is a benchmark that contains multilingual evaluation data used to assess the performance of language models across 200 language directions.
Papers using Flores-200 (7)
- The African Language Tax: Quantifying the Cost, Latency, and Context Penalty of Tokenizing African Languages in Frontier LLMsLLiMba: Sardinian on a Single GPU -- Adapting a 3B Language Model to a Vanishing Romance LanguageDictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language ModelsMufu: Multilingual Fused Learning for Low-Resource Translation with LLMX-ALMA: Plug & Play Modules and Adaptive Rejection for Quality
Translation at ScaleRefining Translations with LLMs: A Constraint-Aware Iterative Prompting
ApproachMarco-LLM: Bridging Languages via Massive Multilingual Training for
Cross-Lingual Enhancement