Unverified50% confidenceFactExact time
The team performed one epoch of fine-tuning on 477,642 synthetic reasoning trajectories distilled from GLM-5.2, covering 22,000 curated problems spanning 16 competitive programming contest systems.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe facts absorbed by large language models during the pre-training phase are encoded in a distributed manner across billions of parameters, with a single fact diffused across the activation patterns of hundreds or even thousands of neurons64% similarVerifiedFine-tuning involves taking an existing large model and further training it with a specially prepared proprietary dataset, thereby changing the model's weight values64% similarUnverifiedWhen model scale crosses from billions of parameters to the hundreds-of-billions level, non-linear emergent capability jumps manifest on code tasks.63% similarUnverified思维链提示与少样本示例可提升7B至14B参数量级模型在复杂编码任务上的成功率63% similarUnverified模型对 schema 的遵循能力受训练数据分布影响，训练语料中高频出现的字段组合会导致模型产生幻觉字段63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958392API
curl https://kongchang.com/api/v1/knowledge/claims/958392MCP
get_claim(id=958392)