The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants

Documenti analoghi

• High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
  di: Franzmeyer, Tim, et al.
  Pubblicazione: (2025)
• The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs
  di: Bandarkar, Lucas, et al.
  Pubblicazione: (2025)
• Emergent Abilities of Large Language Models under Continued Pretraining for Language Adaptation
  di: Elhady, Ahmed, et al.
  Pubblicazione: (2025)
• WiCkeD: A Simple Method to Make Multiple Choice Benchmarks More Challenging
  di: Elhady, Ahmed, et al.
  Pubblicazione: (2025)
• Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models
  di: Elhady, Ahmed, et al.
  Pubblicazione: (2026)