Unverified50% confidenceSolutionExact time
迁移学习可将数据需求从百万级样本降低到每类几百到几千张即可获得不错效果
1
Sources
50%
Confidence
Long-term
Relevance
8/27/2026
First Seen
Sources
Related Entities
Related Claims
Partially VerifiedThe quality of fine-tuning data is far more important than quantity; typically, a few hundred to a few thousand high-quality annotated data samples can significantly improve a model's performance on a specific task.65% similarUnverifiedThe research measured a significant reduction in peak memory usage on a billion-parameter-scale LLM, and the energy savings ratio was higher than the speed improvement ratio.62% similarUnverifiedETH Zurich的研究表明，经过充分域随机化训练的策略，其Sim-to-Real迁移成功率可以从不到30%提升至90%以上61% similarUnverifiedPractical data indicates that well-compressed context can reduce token consumption by 50–80% and improve answer accuracy.60% similarUnverified典型的SFT数据集可能只有数万到数十万条样本，远小于预训练数据规模59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810177API
curl https://kongchang.com/api/v1/knowledge/claims/810177MCP
get_claim(id=810177)