Unverified50% confidenceFactExact time
The paper evaluated nine language models.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/13/2026
First Seen
Valid until: 2/11/2027
Sources
Related Entities
Related Claims
UnverifiedA recent study audited ten open-source models covering eight languages, and in all 70 "model-language" pairings, the non-English stereotype scores were lower than their English levels.79% similarUnverifiedThe study analyzed the word lists of twelve alphabetic writing systems and reported results in detail for five of these languages.77% similarUnverifiedThe study tested six mainstream large language models.77% similarUnverifiedThe study conducted a dual evaluation of 8 large language models, having them serve both as question setters generating misleading options and as answer solvers resolving the problems.74% similarUnverifiedThe study covered 10 frontier models and 3 languages (English, Spanish, Czech), finding that most models are affected by polarity blindness.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1165448API
curl https://kongchang.com/api/v1/knowledge/claims/1165448MCP
get_claim(id=1165448)