Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.01190 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913870230061056 |
|---|---|
| author | Thakur, Madhavendra |
| author_facet | Thakur, Madhavendra |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01190 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Culturally-Grounded Chain-of-Thought (CG-CoT):Enhancing LLM Performance on Culturally-Specific Tasks in Low-Resource Languages Thakur, Madhavendra Computation and Language 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. |
| title | Culturally-Grounded Chain-of-Thought (CG-CoT):Enhancing LLM Performance on Culturally-Specific Tasks in Low-Resource Languages |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.01190 |