Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking

arXiv:2402.09369v1 Announce Type: new
Abstract: Pretrained large language models have revolutionized many applications but still face challenges related to cultural bias and a lack of cultural commonsense knowledge crucial for guiding cross-culture communication and interactions. Recognizing the shortcomings of existing methods in capturing the diverse and rich cultures across the world, this paper introduces a novel approach for massively multicultural knowledge acquisition. Specifically, our method strategically navigates from densely informative Wikipedia documents on cultural topics to an extensive network of …

abstract acquisition applications arxiv benchmarking bias challenges communication cs.cl culture diverse face interactions knowledge knowledge acquisition language language models large language large language models paper type world