Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Tiny Aya Cross-Lingual Medical Concept Probes

Domain:

natural language processing

Record type:

dataset
Creator:
s4u
Host:
20 medical concepts expressed as full sentences in 10 languages, designed for probing cross-lingual concept representations in multilingual LLMs. Each concept is a complete declarative sentence preserving the same semantic structure across all languages. Purpose

Visit

huggingface.co

Languages

AmharicSwahiliYoruba

Tags

mechanistic-interpretabilitycross-lingualmultilingualmedicalprobing

Licenses

apache-2.0

Similar

tiny-aya-blind-spotsTiny Aya Base Blind Spotskeystats/tiny-aya-amharic-healthkeystats/tiny-aya-swahili-healthTiny Aya: Bridging Scale and Multilingual DepthTiny-Aya-Base Blind Spots Evaluation Dataset

tiny-aya-blind-spots

The evaluation of tiny-aya-base on Hausa mathematical reasoning reveals several systematic blind spo

Tiny Aya Base Blind Spots

This dataset documents blind spots identified in CohereLabs/tiny-aya-base, a multilingual base langu

keystats/tiny-aya-amharic-health

keystats/tiny-aya-swahili-health

Tiny Aya: Bridging Scale and Multilingual Depth

Tiny Aya redefines what a small multilingual language model can achieve. Trained on 70 languages and

Tiny-Aya-Base Blind Spots Evaluation Dataset

CohereLabs/tiny-aya-base Architecture: Cohere2 (Cohere Command R family) Parameters: ~3B Type: Raw