想做可靠的科学生成？SFC框架让模型一边写一边用共形预测校验事实，结果比DeepSeek和GPT-4都准，还能少犯73%的科学错误。
SFC是一种基于共形预测的图结构框架，用于自纠正科学生成中的事实性错误。在PhyX多模态物理基准上，SFC达到50.1%的准确率，超过DeepSeek-R1(49.8%)和GPT-4(45.8%)。该框架以91.7%的科学有效性提供形式化共形覆盖保证（置信水平α=0.10），并将科学定律违规率降低73%。SFC通过原子绝对一致事实单元和近似可推导图建模逻辑依赖，在检测到科学违规时动态分支到替代生成路径。
Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation
Large language models frequently violate fundamental scientific principles when generating technical content, undermining their reliability in scientific applications. We introduce Scientific Feasibility Control SFC, a graph-structured conformal prediction framework that provides statistical guarantees for scientific reasoning validity through progressive absolute-coherent-factuality validation. Our approach decomposes scientific reasoning into atomic absolute-coherent-factuality units requiring both individual correctness against physical laws and logical substantiation from preceding context, addressing the cascade effect where early scientific errors contaminate subsequent reasoning steps. Unlike independence-based methods that treat claims in isolation, SFC models logical dependencies as approximate deducibility graphs and operates through real-time validation with dynamic branching when scientific violations are detected, the system branches to alternative generation paths using verified context as foundation. We demonstrate SFC across established scientific reasoning benchmarks including PhyX multimodal physics, MATH, ScienceQA, and ARC Challenge, achieving 50.1 percent accuracy on PhyX physics reasoning, substantially outperforming recent reasoning models including DeepSeek-R1 49.8 percent and GPT-4 45.8 percent while providing 91.7 percent scientific validity with formal conformal coverage guarantees at alpha equals 0.10 confidence level and reducing scientific law violations by 73 percent across multiple model architectures.