Culturally-Grounded Chain-of-Thought (CG-CoT):Enhancing LLM Performance on Culturally-Specific Tasks in Low-Resource Languages
This addresses the challenge of equitable AI deployment by enhancing LLM performance on culturally-specific tasks for low-resource language communities, though it is incremental as it builds on existing prompting techniques.
The paper tackled the problem of LLMs struggling with culturally-specific reasoning tasks in low-resource languages by introducing CG-CoT, a prompting strategy that improved culturally-aligned accuracy and depth in Yoruba proverb interpretation compared to traditional methods.
Large Language Models (LLMs) struggle with culturally-specific reasoning tasks, particularly in low-resource languages, hindering their global applicability. Addressing this gap is crucial for equitable AI deployment. We introduce Culturally-Grounded Chain-of-Thought (CG-CoT), a novel prompting strategy that combines dense vector retrieval of cultural context with explicit reasoning sequences. Our extensive experiments on Yoruba proverb interpretation demonstrate that CG-CoT provides significantly higher culturally-aligned accuracy and depth than traditional prompting methods, validated through both automated metrics and LLM-based evaluations. Notably, we uncover stark disparities between token-level translation metrics like BLEU and human-judged cultural relevance, suggesting a rethinking of evaluation approaches for low-resource NLP.