A package for taking and scoring the PCT
Project description
Political Compass Test (PCT)
- GitHub: https://github.com/isabellahoch/LLM_PCT
- Free software: MIT license
Overview
The Political Compass Test (PCT) is a Python package that allows users to proctor the political compass test algorithmically by allowing LLMs to react to PCT questions with open-ended responses. It classifies responses in agreement levels according to a specified threshold, then directly interacts with the PCT website to determine the generator's political position on the compass.
Features
- Elicits responses to questions for the political compass test
- Classifies generated responses to determine their political position
- Programmatically intearacts with PCT website to take the test and determine results
- Displays PCT results on interactive plot
Setup
Expects a file path to a pct-assetss directory with crx/adblock.crx extension and subdirectories for generated response, score, results files.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file llm_pct-0.0.1.tar.gz.
File metadata
- Download URL: llm_pct-0.0.1.tar.gz
- Upload date:
- Size: 10.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2a382f846d41f091815c361dba87f5e1b70cb4b31a7a2cd88829a92841d06599
|
|
| MD5 |
4dbcb601395a463dbbd0c0e05ead03b3
|
|
| BLAKE2b-256 |
c61bebddde161b973b113b3311761d4a711989b124c7be20463410c5d11bbf4b
|
File details
Details for the file LLM_PCT-0.0.1-py3-none-any.whl.
File metadata
- Download URL: LLM_PCT-0.0.1-py3-none-any.whl
- Upload date:
- Size: 10.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
491226af2115b27630d59d3424d5658f56e9250cdc8259854fd5bd1b874247b3
|
|
| MD5 |
0185b299fe13fa2100734990b64f9c15
|
|
| BLAKE2b-256 |
500ffeb4392e42e5df498cef21886441b3b123dd88276dc0225f12b42ab57911
|
