一作ACL 2026Poster· Natural Language Processing
Common to Whom? Regional Cultural Commonsense and LLM Bias in I ndia
Sangmitra Madhusudan · Trush Shashank More · Steph Buongiorno · Renata Dividino · Jad Kabbara · Ali Emami
摘要
Existing cultural commonsense benchmarks treat nations as monolithic, assuming uniform practices within national boundaries. But does cultural commonsense hold uniformly within a nation, or does it vary at the sub-national level? We introduce Indica , the first benchmark designed to test LLMs’ ab...