jevTHREAD
质疑 Jev「无幻觉」说法：schema 保证来自推理框架
作者认为 Jev 的 schema 安全只是分类模型或并行约束解码的推理算法，靠 outlines 这类引导库自回归模型也能做到。
AVB
@neural_avb2026.09.21收录原推发布于 2026.09.21
THREAD
My issue really is them claiming "no-hallucination" coz of the schema safety. Even Autoregressive LLMs can guarantee schema using low-level guidance libraries like outlines. Since JEV is a classification model, or a parallel constraiend decoder - the schema guarantee is largely a inferencing algorithm. Its NOT the capability of the underlying model, but the harness around it.
To be clear, it makes total sense in a network architecture sense. JEV is a language model. Token representations depend on the input state, and TypeSafe team is likely packing the full list of choices as a list of options into the prompt... So choice order changes probabilities.
AVB @neural_avb原推发布于 2026.09.21
x.com/neural_avb/status/2101738806173122973采集于 2026.09.21 10:14