LLMs Spot Social Challenges in South African Languages

Kari Jaaskelainen

24 Nov 2025 — 1 min read

Can AI help governments hear the public—across languages? This new study tests large language models (LLMs) on South African social media, analyzing sentiment on the top 10 emerging topics in English, Sepedi, and Setswana.

What they tested: GPT-3.5, GPT-4, Llama 2, PaLM 2, and Dolly 2 in zero-shot mode.
Where: Posts tied to 10 South African government departments.
Key finding: Big differences across models, topics, and languages.
Breakthrough: Fusing model outputs (an ensemble) cut reported errors to under 1%.
So what: Reliable, multilingual sentiment signals can now flag social challenges early and guide targeted action.

Paper: https://arxiv.org/abs/2511.17301v1

Note: Any real-world rollout should protect privacy and include human oversight.

Paper: https://arxiv.org/abs/2511.17301v1

Register: https://www.AiFeta.com

#AI #LLM #SentimentAnalysis #SouthAfrica #MultilingualAI #GovTech #PublicPolicy #SocialMedia #Sepedi #Setswana

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added