文化根基链式思维（CG-CoT）：提升大语言模型在低资源语言文化特定任务上的表现
Culturally-Grounded Chain-of-Thought (CG-CoT):Enhancing LLM Performance on Culturally-Specific Tasks in Low-Resource Languages
AI总结：
本文提出文化根基链式思维（CG-CoT）提示策略，通过融合文化语境稠密向量检索与显式推理，显著提升大语言模型在约鲁巴谚语解释等低资源语言文化特定任务上的表现，并揭示现有翻译评估指标与文化相关性判断之间的显著差异。
摘要：
大语言模型（LLMs）在文化特定推理任务上表现不佳，尤其是在低资源语言中，这阻碍了其全球适用性。解决这一差距对于公平部署人工智能至关重要。我们提出了文化根基链式思维（CG-CoT），这是一种新颖的提示策略，将文化语境的稠密向量检索与显式推理序列相结合。我们在约鲁巴谚语解释上的大量实验表明，CG-CoT 在文化对齐准确性和深度上显著优于传统提示方法，并通过自动指标和基于大语言模型的评估得到了验证。值得注意的是，我们发现了 BLEU 等词元级翻译指标与人类评判的文化相关性之间存在显著差异，这表明需要重新思考低资源自然语言处理的评估方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
