AI Writing Markers: Building an Open Dataset and Checker on Hugging Face
说明与用途
ai‑writing‑markers 工具提供透明、来源支持的文本分析,突出 LLM 风格模式,帮助作者在不依赖不透明概率分数的情况下编辑草稿。
问题
Commercial AI detectors give opaque probability scores with high false‑positive rates, especially against non‑native English writers.
结果
The checker provides transparent, source‑backed feedback on AI‑like writing patterns, empowering users to edit drafts without relying on opaque probability scores.
工作流
- Clone the ai‑writing‑markers repo
- Run
python3 check.py <file>or pipe text to the checker - Review the per‑category hit counts and source‑backed markers
- Edit the draft to reduce dense clusters of flagged patterns
- Re‑run the checker to confirm improvements
证据
Markers are weak signals. One instance of "delve" means almost nothing.
The honest thing a tool can do is point at the patterns that make writing read as machine‑generated — so a human can decide whether to change them.
The checker loads markers.json, runs lexical matching per category, applies regex patterns for structural and formatting tells, and computes burstiness plus type‑token ratio as perplexity proxies.
- 记录日期: 2026-09-05T15:28:37.167Z