Unverified50% confidenceFactExact time
Zero-shot models require no labeled data; simply writing out labels in natural language is enough to produce classification results.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedZero-shot classifiers (such as solutions based on CLIP or NLI) allow users to describe categories in natural language, offering greater flexibility but typically requiring a larger base model.75% similarUnverifiedWhen few-shot examples demonstrating label contrasts are included in the prompt, all large language models outperform zero-shot prompting.75% similarVerifiedZero-shot classification relies on the semantic understanding capabilities of pretrained large language models such as NLI variants of BART and RoBERTa.73% similarUnverifiedZero-shot prompting refers to providing no examples and relying entirely on textual descriptions.73% similarUnverifiedAnother implementation of zero-shot classification is to directly call instruction-following large language models (such as GPT-4 and Claude), using prompts to describe classification rules and output category labels.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/976262API
curl https://kongchang.com/api/v1/knowledge/claims/976262MCP
get_claim(id=976262)