Unverified60% confidenceFactExact time
Multiple academic studies in 2023 confirmed the feasibility of cross-lingual jailbreak attacks, finding that model refusal rates dropped significantly after translating harmful requests into low-resource languages such as Zulu and Georgian.
2
Sources
60%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
Unverified将英语有害提示翻译为祖鲁语、格鲁吉亚语、泰语等低资源语言后，GPT-4、Claude等模型的拒绝率可从接近100%骤降至30%-50%77% similarUnverifiedMultiple academic studies have found that translating the same harmful question from English into low-resource languages significantly reduces the refusal rate of mainstream LLMs.76% similarUnverified低资源语言中相当一部分面临数字化消亡风险（联合国教科文组织估计）70% similarUnverifiedSince 2023, the widespread adoption of large language models has lowered the barrier to bulk-generating seemingly well-sourced articles, comments, and even academic abstracts.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/532881API
curl https://kongchang.com/api/v1/knowledge/claims/532881MCP
get_claim(id=532881)