Unverified50% confidenceFactExact time
After supervised fine-tuning (SFT), the gains brought by UpLoop can also extend to mathematical reasoning tasks.
1
Sources
50%
Confidence
Long-term
Relevance
11/2/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在推理阶段追加FLOPs能带来显著的能力提升69% similarUnverifiedUpLoop has so far mainly validated language modeling and mathematical reasoning scenarios, and its generalization ability on broader tasks remains to be further observed.69% similarUnverifiedSFT is not installing a chat module into the model, but performing a large-scale reweighting of the probability distribution to increase the probability of the reference answer sequence.68% similarUnverified推理时计算（Inference-time Compute）的扩展能提升单次输出质量，但成本以超线性方式增长65% similarUnverifiedLarge model fine-tuning engineers (SFT direction) are one of the fastest-growing areas of enterprise demand, because enterprises often perform SFT supervised fine-tuning and LoRA fine-tuning on existing models using internal data rather than training models from scratch.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1125020API
curl https://kongchang.com/api/v1/knowledge/claims/1125020MCP
get_claim(id=1125020)