English

The 'English' dataset/benchmark contains 50 hand-crafted questions across various categories and is used to evaluate the performance of large language models on accuracy, fluency, and completeness in comparison to low-resource languages.

Papers using English (7)

Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats2026Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models2026Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection2026MUTANT: A Recipe for Multilingual Tokenizer Design2025Testing Cross-Lingual Text Comprehension In LLMs Using Next Sentence Prediction2025How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis2025CEA-LIST at CheckThat! 2025: Evaluating LLMs as Detectors of Bias and Opinion in Text2025