Seyed Ehsan Hadi writes about a local command-line tool and agent plugin that scores prose files for LLM-writing patterns using only the Python standard library, with no network access and no model. It works by hooking into coding agents like Claude Code to evaluate files saved on disk, flagging 71 documented patterns to prompt rewrites.
- Uses stylometry and lexical checks rather than an LLM
- Achieved a ROC-AUC of 0.946 on the GPT-4o benchmark arm
- Supports 20 file formats including .docx, .epub, and .ipynb
- Explicitly warns against using its scores as an authorship classifier
- Uses stylometry and lexical checks rather than an LLM
- Achieved a ROC-AUC of 0.946 on the GPT-4o benchmark arm
- Supports 20 file formats including .docx, .epub, and .ipynb
- Explicitly warns against using its scores as an authorship classifier
XTRAN is a software meta-tool that marries compiler and expert system technologies to provide rule-driven automation of software tasks involving a wide variety of computer languages. It supports code assessment, generation, transformation, translation, data/text analysis, and more.
This page details the topic namers available in Turftopic, allowing automated assignment of human-readable names to topics. It covers Large Language Models (local and OpenAI), N-gram patterns, and provides API references for the `TopicNamer`, `LLMTopicNamer`, `OpenAITopicNamer`, and `NgramTopicNamer` classes.
MegaParse is an open-source tool designed for parsing and converting various types of documents for ingestion into LLM. It supports multiple document formats, including text, PDF, PowerPoint, Excel, CSV, and Word documents, and offers customizable output formats to meet different LLM requirements, making it a versatile and efficient solution for data preparation in LLM applications.
This article explains how to use Large Language Models (LLMs) to perform document chunking, dividing a document into blocks of text that each express a unified concept or 'idea', to create a knowledge base with independent elements.
This article explores the use of word2vec and GloVe algorithms for concept analysis within text corpora. It discusses the history of word2vec, its ability to perform semantic arithmetic, and compares it with the GloVe algorithm.
