Unverified85% confidenceFactTime unknown
部分研究者认为大模型涌现能力是真实的相变现象，另一些人认为这只是评估指标选择造成的统计假象
1
Sources
85%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
Unverified文生图模型的理解本质上是大规模的统计关联而非真正的推理理解76% similarUnverified思维链推理的效果随模型规模呈现涌现性，在较小模型上几乎无效，在足够大的模型上才能显著提升推理准确率75% similarUnverifiedWhen selecting models, one should not only look at accuracy on standard datasets but also pay attention to out-of-domain generalization robustness on unfamiliar data.73% similarUnverifiedThe probability figures provided by guided generative models are essentially 'well-constrained inferences' rather than directly verifiable truths.71% similarVerifiedThe technical root cause of hallucination in large models lies in the autoregressive generation mechanism, where the model predicts only the statistically most likely next token based on the preceding context; researchers divide hallucinations into intrinsic hallucinations and extrinsic hallucinations.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/7304API
curl https://kongchang.com/api/v1/knowledge/claims/7304MCP
get_claim(id=7304)