AI4LIFE-GROUP/LLM_Explainer
Code for paper: Are Large Language Models Post Hoc Explainers?
This project helps machine learning practitioners understand why their classification models make certain decisions. It takes a trained model and a dataset, then uses large language models (LLMs) to generate human-readable explanations for individual predictions. The goal is to evaluate if LLMs can effectively explain complex model behavior, providing insights to data scientists or domain experts.
No commits in the last 6 months.
Use this if you are a machine learning researcher or data scientist investigating the interpretability of your classification models, especially when exploring how large language models can generate post-hoc explanations.
Not ideal if you need a user-friendly, out-of-the-box explainability tool for immediate deployment in a business application, as this project is research-focused and requires a technical understanding of ML pipelines and LLM prompting.
Stars
34
Forks
5
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/AI4LIFE-GROUP/LLM_Explainer"
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.
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