Academic text polisher and humanizer for Chinese and English research writing. Removes AI-like patterns while preserving factual accuracy. Use when polishing academic text, reducing AI-generated patterns in papers/theses, improving naturalness of research writing while maintaining data integrity, or enhancing scholarly tone without fabricating facts. Supports both Chinese (中文) and English academic texts with configurable tone, field-specific terminology, and strict factuality controls.
Polish and humanize academic writing to reduce AI-like patterns while preserving all factual content, data, and meaning.
Apply the system prompt from references/system_prompt.md and use the workflow below.
Always produce exactly 4 sections:
Non-negotiable:
Remove AI-isms:
See references/phrase_blacklist.md for complete list.
Configure behavior using these parameters:
auto (detect) | zh (Chinese) | en (English)formal (default) | semi-formal | concise | persuasivetrue (default) - preserve all data/factstrue (default) - preserve citation markershigh (default) | medium | lowFor domain-specific terminology or special requirements, see:
references/system_prompt.md - Complete editing principles and constraintsreferences/phrase_blacklist.md - AI-pattern phrases to avoidreferences/user_template.md - Parameterized user prompt templateUse the CLI wrapper for batch processing:
# Process a text file
python3 scripts/paper_humanizer.py --text-file input.txt --language auto
# Generate composed prompt for external use
python3 scripts/paper_humanizer.py --text-file input.txt --out prompt.md
The script combines system prompt and user template with specified parameters.34:["$","$L3c",null,{"content":"$3d","frontMatter":{"name":"paper-humanizer","description":"Academic text polisher and humanizer for Chinese and English research writing. Removes AI-like patterns while preserving factual accuracy. Use when polishing academic text, reducing AI-generated patterns in papers/theses, improving naturalness of research writing while maintaining data integrity, or enhancing scholarly tone without fabricating facts. Supports both Chinese (中文) and English academic texts with configurable tone, field-specific terminology, and strict factuality controls."}}]