04:00
2026-07-01
arxiv.org
large-language-models
Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions
Researchers introduced Indi-RomCoM, a benchmark for evaluating large language models on Romanized code-mixed Indic-English instructions. Testing across seven tasks and four languages showed that LLMs …