🇵🇭 FilBench - Can LLMs Understand and Generate Filipino?

🇨🇿 BenCzechMark - Can your LLM Understand Czech?

Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance

Open-source LLMs as LangChain Agents

Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs

CyrillicQA: The Influence of Phonetically Encoded Secret Language on LLM Performance

arXiv:2608.21462v1 Announce Type: cross Abstract: Due to the selection of their training data, large language models (LLMs) perform best on standard-language inputs from languages using the Latin alp...

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context