arXiv:2606.03304v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains underexplored especially under pure prompting without fine-tuning. We present a systematic study of prompting strategies for Natural Language Inference (NLI) in Swahili, Yoruba, and Hausa using the AfriXNLI benchmark. We evaluate five prompting strategies Baseline (zero-shot), Script-Aware, Language Specific, Contrastive, and Native-Label Self-Translation (NL-STP) across two mid-sized open weight
The increasing focus on multilingual LLMs and the recognition of data-scarce languages are driving this timely research into effective prompting strategies.
This research provides crucial insights into optimizing LLM performance for underrepresented African languages, directly impacting the accessibility and utility of advanced AI in diverse linguistic contexts.
Understanding effective prompting methods without fine-tuning can significantly lower the barrier to deploying robust AI solutions in low-resource language environments.
- · African AI developers
- · Multilingual LLM providers
- · African language communities
- · AI ethics researchers
- · Monolingual AI research paradigms
- · Organizations relying solely on high-resource language data
Improved performance of LLMs in African languages through specific prompting strategies.
Increased adoption and utility of AI technologies within African nations, fostering localized innovation.
Enhanced digital inclusion and economic growth in African countries as language barriers to AI applications diminish.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL