jevIMAGE
复现:Jev 类决策模型概率并不自洽
作者在天气预报任务上复现论文,发现把命题取反后 P(A)+P(非A)>1,决策模型有时还不如普通 LLM。
Shuvom Sadhuka
@shuvom_s19 天前收录原推发布于 2026.10.11

Shuvom Sadhuka @shuvom_s原推发布于 2026.10.11
Decision models like Jev are getting a lot of hype right now, but are decision models I actually probabilistically coherent? What happens if you flip the predicate from "it will rain" to "it will NOT rain"? Turns out, not only do they give incoherent answers (e.g., P(A) + P(not A) > 1), but they're sometimes WORSE than standard LLMs. I recreated this work from @SuproteemSarkar and Isaiah Andrews on a simple weather forecasting task using OpenAI's new decision model.
这条是引用着另一条写的:x.com/suproteemsarkar/status/2095904452225990966
x.com/shuvom_s/status/2109013068609167479采集于 2026.10.12 10:05