llmshield.matchers.dicts package

Module contents

Dictionary data files for entity matching.

Description:

This subpackage contains text files with known entities used for dictionary-based entity detection. These files include lists of cities, countries, organisations, and common English words used to improve entity classification accuracy.

Data Files:

• cities.txt: List of world cities

• countries.txt: List of countries and territories

• organisations.txt: List of known organisations

• english_corpus.txt: Common English words for filtering

Author:

LLMShield by brainpolo, 2025