mlsanityData to 7 Oct 2026

Geometric Representations of African Languages: A Regional Semantic Hub and Cultural Steering

arXiv 2609.36205 ↗First posted 28 Sep 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

We study how Gemma 4 31B represents African languages and responds to cultural steering. The first study compares nine African languages and three controls using probes, contrast directions, and measures of representation similarity. Transfer from English varies across languages and layers. Directions representing an Africa versus West contrast are more aligned among the African languages than between these languages and the controls at several layers. The comparison across language families passes the reported Holm threshold at five of twelve layers, although dependence between language pairs limits the statistical interpretation. Within Nigeria, Yoruba and Igbo are more aligned than the average of their pairs with Hausa at eleven of twelve layers. The second study uses separate English data to construct directions for Nigeria, Ghana, Kenya, and South Africa. Under union scoring at the selected strengths, estimated differences in attribution rates from random directions range from 0.63 to 0.81. Most outputs pass the automated structural coherence screen. Comparisons with Aya Expanse 32B show that results depend on the representation measure. Together, the studies document regional and family patterns in the sampled representations and country steering in English.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 20 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

13 of 20 references.

References · 13

  1. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  2. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  3. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  4. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,009
  5. 2024Refusal in Language Models Is Mediated by a Single Directioncited by 960
  6. 2019How multilingual is Multilingual BERT?cited by 642
  7. 2024Do Llamas Work in English? On the Latent Language of Multilingual Transformerscited by 275
  8. 2020Participatory Research for Low-resourced Machine Translation: A Case Study in African Languagescited by 159
  9. 2024Investigating Cultural Alignment of Large Language Modelscited by 140
  10. 2024The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalitiescited by 69
  11. 2025Localized Cultural Knowledge is Conserved and Controllable in Large Language Modelscited by 19
  12. 2026Steering LLMs for Culturally Localized Generationcited by 4
1 more
  1. 2026Cultural Value Alignment Via Latent Activation Steering in Large Language Modelscited by 3

Built on by

Not cited yet.