The Geometry of Low-Resource Language Representations
The performance gap between low- and high-resource languages in LLMs is widely known, but it remains unclear which internal model factors drive these disparities. In this paper, we characterise this gap through the lens of representational geometry. Comparing the geometric properties of hidden representations across 30 languages reveals that LLM geometry is systematically related to language data availability. The most consistent effect is in final layers, where low-resource languages exhibit representational degeneration. To counter this, we investigate the effectiveness of regularisation ter
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%New Server Hopes to Break Through AI’s “Memory Wall” →
- PossiblePossibly related (embedding) · 55%Mortif Technologies' own Large Language Model (LLM) ranked third among open weight models in the glo.. - 매일경제 →
- PossiblePossibly related (embedding) · 53%Are Large Language Models Getting Smaller? Key Trends, Benefits and Real-World Use Cases in 2024 - 36 Kr →
- LinkedLinked via arxiv author · 85%Francois Meyer →
“The Geometry of Low-Resource Language Representations”
- LinkedLinked via arxiv author · 85%Jan Buys →
“The Geometry of Low-Resource Language Representations”