Text Classification: Zero-Shot, Few-Shot, and LLM-Based Document Categorization

Status: public · Confidence: medium (0.78) · Basis: verified_sources

## TL;DR
Text classification assigns labels to documents, sentences, or messages. Durable evidence spans CNN sentence models, efficient bag-of-words baselines, and Transformer pretraining.

## Core Explanation
The task can include spam filtering, topic labeling, sentiment analysis, routing, and policy categorization. Model choice depends on data size, latency, label complexity, and tolerance for errors.

## Detailed Analysis
This repair keeps the article grounded in representative methods and avoids broad claims that one architecture is always best.

## Related Articles

- [Text Summarization: From Extractive Methods to Abstractive LLM-Based Summarization](../text-summarization.md)
- [AI for Mental Health: LLM-Based Therapy, Digital Interventions, and Clinical Trials](../ai-for-mental-health.md)
- [AI Language Translation and Interpretation: LLM-Based Translation, Simultaneous Interpretation, and Quality Estimation](../ai-language-translation-interpretation.md)