LFhase/CausalCOAT
[NeurIPS 2024] Discovery of the Hidden World with Large Language Models
This project helps researchers and data scientists uncover hidden relationships and underlying causes from complex text data, such as product reviews or clinical notes. It takes in raw text data and leverages large language models to identify influential factors and their causal links, providing a clearer understanding of why certain outcomes occur. Anyone needing to find non-obvious causal connections within qualitative data, like market researchers, social scientists, or medical researchers, would benefit from this.
No commits in the last 6 months.
Use this if you have text data and suspect there are 'hidden' causal factors influencing observed outcomes that traditional statistical methods might miss.
Not ideal if your data is purely numerical and you are looking for standard statistical correlations without needing to interpret free-form text.
Stars
8
Forks
5
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/LFhase/CausalCOAT"
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