Unverified50% confidenceFactExact time
PRSR uses multilingual parallel sentences to construct pairwise residuals, estimates a layer-wise low-rank subspace from the residuals, and suppresses language-specific components in the final-layer token hidden states.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
Unverified大语言模型难以编码为什么在特定社会语境中词的真实含义与字面意义相反这类元认知推理，这一局限被称为'语用鸿沟'（pragmatic gap）64% similarUnverifiedCross-lingual jailbreaking exploits the asymmetry between a model's concept space and its language space, as the learning of safety-refusal behavior is highly language-specific.63% similarUnverifiedThe key difference between disagreement-guided steering and post-hoc debiasing methods such as language mean removal, subspace removal, and per-language rotation is that it uses the dynamic signal of disagreement among retrieval results rather than global statistics of languages.62% similarUnverifiedParalinguistic factors (speaker identity, emotion, prosody) are preserved in the paralinguistic route and significantly reduced in the linguistic route.62% similarUnverifiedCross-lingual transfer in multilingual models mainly relies on a shared multilingual representation space, which exhibits a significant alignment gap between language pairs with large differences in grammatical structure.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064854API
curl https://kongchang.com/api/v1/knowledge/claims/1064854MCP
get_claim(id=1064854)