Unverified50% confidenceFactExact time
Few-shot prompting does not modify model weights; it constrains the output distribution through context only at inference time, unlike fine-tuning in traditional machine learning.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedModel capability cannot be judged by parameter scale alone, as model performance is influenced by multiple factors including training data distribution, reasoning pathways, and randomness.78% similarUnverified提示词并没有真正提高模型的能力，它只是给模型提供了更多相关信息77% similarUnverifiedGrammar-constrained decoding does not alter the model's weights or training process; it only acts as a safety net during the inference stage, and the relative probability ranking among legal tokens remains unchanged.76% similarUnverifiedSimply stacking compute and scaling parameters cannot give transductive models fluid intelligence; it is the paradigm shift from guessing answers to constructing reasoning programs that brings about a qualitative leap.76% similarVerifiedThe prompts submitted to the models did not include question-type hints, requiring the models to determine the question type on their own.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/996904API
curl https://kongchang.com/api/v1/knowledge/claims/996904MCP
get_claim(id=996904)