Unverified50% confidenceFactExact time
The Transformer architecture computes a probability distribution over all tokens in the vocabulary at each decoding step via the softmax function, then selects the next token through sampling strategies such as temperature and top-p.
1
Sources
50%
Confidence
Long-term
Relevance
9/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLM基于Transformer架构的自注意力机制和Softmax概率分布，通过温度参数控制采样随机性，温度趋近0时输出最高概率token，温度升高时引入更多随机性76% similarUnverifiedLarge language models are based on the Transformer architecture, and their output is essentially a probabilistic sampling process, with the Temperature parameter controlling the randomness of sampling.75% similarUnverifiedLLM在每个生成步骤输出的是词汇表上的完整概率分布，通常通过softmax函数计算72% similarUnverifiedLarge language models use the self-attention mechanism in the Transformer architecture to compute the probability distribution of all candidate tokens at each position71% similarUnverifiedTransformer模型通过注意力机制（Self-Attention）在推理阶段在词汇表上生成一个概率分布，再通过温度参数（Temperature）调节分布的平坦度，温度越高输出越随机多样，温度越低越趋向高概率词元70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/840324API
curl https://kongchang.com/api/v1/knowledge/claims/840324MCP
get_claim(id=840324)