Prompt Engineering for Nepali NER: Leveraging Hindi-Capable LLMs for Low-Resource Languages

Dipendra Yadav, Sumaiya Suravee, Stefan Kemnitz, Tobias Strauss, Kristina Yordanova


Abstract
This study provides a systematic evaluation of prompt engineering strategies for Named Entity Recognition in Nepali, a low-resource language with high similarity to Hindi, by leveraging Hindi-capable Meta’s LLaMA 3.3:70B model. Four prompting techniques—Baseline, Chain-of-Thought, Self-Refine, and Least-toMost—are assessed in both zero-shot and fewshot settings. As a novel contribution, we propose an entity-aware sentence selection strategy that prioritizes example diversity and entity coverage for few-shot prompting. Experimental results show that, without Nepali examples, zero-shot and one-shot prompts frequently yield unstructured or hallucinated outputs, underscoring the limitations of cross-lingual capabilities without in-context supervision. However, including even a small number of carefully selected Nepali examples—sometimes as few as ten—substantially enhances model performance, with the Least-to-Most approach achieving the highest F1 scores. These findings highlight the potential of prompt-based adaptation and principled example curation for extending LLM capabilities to related, low-resource languages, offering a practical alternative to full model fine-tuning.
Anthology ID:
2025.ranlp-1.158
Volume:
Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
Month:
September
Year:
2025
Address:
Varna, Bulgaria
Editors:
Galia Angelova, Maria Kunilovskaya, Marie Escribe, Ruslan Mitkov
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
1364–1373
Language:
URL:
https://aclanthology.org/2025.ranlp-1.158/
DOI:
Bibkey:
Cite (ACL):
Dipendra Yadav, Sumaiya Suravee, Stefan Kemnitz, Tobias Strauss, and Kristina Yordanova. 2025. Prompt Engineering for Nepali NER: Leveraging Hindi-Capable LLMs for Low-Resource Languages. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1364–1373, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Prompt Engineering for Nepali NER: Leveraging Hindi-Capable LLMs for Low-Resource Languages (Yadav et al., RANLP 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.ranlp-1.158.pdf