Unverified50% confidenceFactExact time
Few-shot examples refer to task demonstration samples provided to the model in the prompt, usually presented as input-output pairs; zero-shot prompting relies only on instructions to describe the task.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPrompt engineering guides a general-purpose model to complete a task by designing input instructions, examples and output formats without modifying model parameters, and has the lowest iteration cost.79% similarUnverifiedThe task_input values are a fixed enum from the vocabulary of task prompts defined during model training (such as <CAPTION>, <OD>, <CAPTION_TO_PHRASE_GROUNDING>, etc.); choosing the wrong one or inventing a task name will not raise an error, and the model will merely degrade to generic description output.75% similarUnverifiedPrompt engineering typically encompasses multiple layers, including System Prompts, Few-shot Examples, and Chain-of-Thought Prompting.72% similarUnverifiedOne-shot generation refers to a user entering a prompt and the model directly outputting a complete runnable program, commonly seen in scenarios such as small games and simple tools.72% similarUnverifiedSimple tasks (such as classification and grammar correction) can use smaller, cheaper models rather than the largest model, and matching the model to the task reduces costs.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129066API
curl https://kongchang.com/api/v1/knowledge/claims/1129066MCP
get_claim(id=1129066)