microsoft/augmented-interpretable-models
Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.
When analyzing text data, this project helps you build classification or regression models that are both accurate and easy to understand. You input text snippets and corresponding labels (like sentiment or categories), and it outputs predictions along with clear explanations of which words or phrases most influenced the outcome. This is useful for data scientists, machine learning engineers, or researchers who need to explain their text-based models' decisions.
Use this if you need to understand why your text classification or regression models make certain predictions, rather than just getting an answer.
Not ideal if your primary goal is only maximizing prediction accuracy without any need for interpretability.
Stars
44
Forks
12
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/microsoft/augmented-interpretable-models"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MadryLab/context-cite
Attribute (or cite) statements generated by LLMs back to in-context information.
Trustworthy-ML-Lab/CB-LLMs
[ICLR 25] A novel framework for building intrinsically interpretable LLMs with...
poloclub/LLM-Attributor
LLM Attributor: Attribute LLM's Generated Text to Training Data
THUDM/LongCite
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
UKPLab/5pils
Code associated with the EMNLP 2024 Main paper: "Image, tell me your story!" Predicting the...