Naive Bayes
AssessTechniques
A probabilistic classification method often used as a baseline for text classification.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 4Hacker News·7/16/2026researchClassical ML for Detecting LLM-Generated Text
An article describes an experimental approach to detecting AI-generated text using traditional machine learning rather than large language model-based scoring. The author reports that linear SVM and Naive Bayes classifiers can separate human-written and LLM-generated text with around 85% single-sentence accuracy in a demo, while noting limitations and generalization issues.