Unverified50% confidenceFactExact time
Zero-shot LLMs are often worse than simple baseline methods on prediction tasks such as determining whether a given layer has been fine-tuned and estimating the order of magnitude of a model's parameter count.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUpon each new observation, SLICE generates simulated data from the corresponding model for each candidate null hypothesis parameter value, and uses it to conformalize positive-predictable scores, converting them into conditional e-values.76% similarUnverified零样本能力指模型在未经针对该任务专项训练的情况下直接完成推理,是衡量模型是否内化物理化学规律的试金石76% similarVerifiedA zero-shot model can make predictions directly on a new dataset it has never seen before, without task-specific retraining or fine-tuning.75% similarUnverified系统提示词是一种零样本引导方式,在推理阶段调控模型行为,不同于微调会改变模型的权重参数74% similarUnverifiedThe first step in evaluating an LLM should be to clarify what is to be measured, rather than running the model directly73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129812API
curl https://kongchang.com/api/v1/knowledge/claims/1129812MCP
get_claim(id=1129812)