Unverified50% confidenceFactExact time
The causal attention mask of Transformer ensures that predictions at each position depend only on historical information by setting the upper triangular portion of the attention matrix to negative infinity.
1
Sources
50%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Kronos金融基础模型：用AI读懂K线市场语言
Related Claims
VerifiedThe self-attention mechanism of the Transformer can capture dependencies between any two positions in a sequence, and regardless of how far apart the tokens are, the computational cost of calculating attention weights is the same79% similarUnverifiedTransformer架构的注意力机制决定了模型只能处理当前上下文窗口内的信息76% similarUnverifiedTransformer注意力层存在位置偏置，模型对序列起始位置(primacy bias)和末尾位置(recency bias)的关注天然高于中间段落76% similarUnverifiedBecause the Transformer self-attention mechanism exhibits positional bias, earlier input content has a stronger anchoring effect on subsequent generation, which is the underlying reason for the context anchoring effect of system prompts75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/600068API
curl https://kongchang.com/api/v1/knowledge/claims/600068MCP
get_claim(id=600068)