surface↓classification↓virality_llm
Classificationdimension · returns varchar

VIRALITY_LLM

LLM-backed virality prediction (escape hatch for VIRALITY)

Per-row classifier — stable across GROUP BY.

classificationllmllm-escape-hatchtext

Arguments

nametypedescription
textVARCHAR—
mechanismVARCHAR—

About

LLM-backed alternative to VIRALITY for predicting whether a piece of content is likely to go viral. Reach for this when the base NLI operator can't read the social dynamics behind the text — timing, cultural references, in-joke signals, outrage triggers — and you need judgment-heavy reasoning rather than label-matching. Like VIRALITY, it supports an optional `mechanism` argument to focus the prediction on a specific viral driver (humor, outrage, inspiration, controversy, novelty). For content-strategy workflows scoring thousands of posts, VIRALITY is far cheaper and good enough for trend detection. Use the LLM variant on edge cases.

Examples

LLM escape hatch predicts virality

SELECT
  virality_llm ('You wont believe what happens!')

Nearby rabbit holes

same domain
dimension

AUDIENCE

Identify target audience via zero-shot NLI

classificationnlispecialist-zootext+1
dimension

AUDIENCE_LLM

LLM-backed audience identification (escape hatch for AUDIENCE)

classificationllmllm-escape-hatchtext
dimension

AUTHENTICITY

Assess authenticity of content via zero-shot NLI

classificationnlispecialist-zootext
dimension

AUTHENTICITY_LLM

LLM-backed authenticity assessment (escape hatch for AUTHENTICITY)

classificationllmllm-escape-hatchtext
dimension

BUCKET

Classify text into user-specified buckets via zero-shot NLI

classificationnlispecialist-zootext
dimension

BUCKET_LLM

LLM-backed bucketing (escape hatch for BUCKET)

classificationllmllm-escape-hatchtext
Climb back to The Looking Glass