Trustworthy-ML-Lab/CB-LLMs
[ICLR 25] A novel framework for building intrinsically interpretable LLMs with human-understandable concepts to ensure safety, reliability, transparency, and trustworthiness.
This framework helps AI developers build Large Language Models (LLMs) that are transparent and explainable. Instead of a 'black box' that just gives answers, this system takes text data and produces an LLM that not only generates or classifies text but also shows *why* it made a particular decision, using human-understandable concepts. It's designed for machine learning engineers and researchers who need to ensure the safety, reliability, and trustworthiness of their LLM applications.
Use this if you need to develop an LLM for text generation or classification where understanding the model's reasoning process and ensuring its reliability is crucial.
Not ideal if your primary concern is only raw predictive accuracy without any need for transparency or interpretability in the model's decisions.
Stars
31
Forks
18
Language
Python
License
—
Category
Last pushed
Feb 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Trustworthy-ML-Lab/CB-LLMs"
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.
microsoft/augmented-interpretable-models
Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.
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...