gabe-mousa/Apolien
AI Safety Evaluation Library
Implements chain-of-thought faithfulness evaluation by intervening in model reasoning steps to detect post-hoc explanations versus genuine reasoning, supporting local models via Ollama and cloud APIs (Claude, OpenAI) through a unified evaluator interface. Runs safety tests across configurable datasets with file-based logging of conversation transcripts and results. Currently focuses on faithfulness detection with extensible architecture for additional safety metrics like sycophancy and deception.
Available on PyPI.
Stars
5
Forks
1
Language
Python
License
MIT
Category
Last pushed
Dec 09, 2025
Monthly downloads
107
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/gabe-mousa/Apolien"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
microsoft/promptbench
A unified evaluation framework for large language models
uptrain-ai/uptrain
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications....
microsoftarchive/promptbench
A unified evaluation framework for large language models
babelcloud/LLM-RGB
LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.
PromptMixerDev/prompt-mixer-app-ce
A desktop application for comparing outputs from different Large Language Models (LLMs).