Unverified50% confidenceFactExact time
FIDEL was evaluated on three Ethiopian languages, with the corpus, architecture, budget and protocol held fixed in the experiments and tokenization as the only variable.
1
Sources
50%
Confidence
Long-term
Relevance
11/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe FIDEL study covers only three Ethiopian languages, and its generalizability remains to be verified.74% similarUnverifiedMultilingual models such as mT5 and Llama 3 explicitly design language budgets when building tokenizers, allocating vocabulary slots by writing system or language family.61% similarUnverifiedThis work is the first to systematically reveal the language-conditioned geometry problem in multilingual training-free text embeddings.59% similarUnverifiedFIDEL extends the SPLINTER reduction method from abjad scripts to Ethiopian abugida scripts.59% similarUnverifiedThe study conducted experiments on three tasks: screening harmful requests to large language models, qualitative text annotation, and data annotation.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1178447API
curl https://kongchang.com/api/v1/knowledge/claims/1178447MCP
get_claim(id=1178447)