Interpretable machine learning based on Shapley values

A repository to study the interpretability of time series networks(LSTM)

Deep Classiflie is a framework for developing ML models that bolster fact-checking efficiency. As a POC, the initial alpha release of Deep Classiflie generates/analyzes a model that continuously classifies a single individual's statements (Donald Trump) using a single ground truth labeling source (The Washington Post). For statements the model d…

Accompanying code for the paper "Discrete representations in neural models of spoken language" (https://aclanthology.org/2021.blackboxnlp-1.11)

Demos for visualizing how rule-based models work.

Training and exploration of linear probes into Othello-GPT by Li et al. (2022)

Demonstration of InterpretME, an interpretable machine learning pipeline

a module to obtain diverse real-world-grounded features for sentences for large-scale benchmarking

Official Implementation of ARACHNET: INTERPRETABLE SUB-ARACHNOID SPACE SEGMENTATION USING AN ADDITIVE CONVOLUTIONAL NEURAL NETWORK

Implementation for the ACL-Findings 2024 paper on memorisation localisation for NLP classification tasks.

📚 Curated list for Causality and AI

A framework for conducting interpretability research and for developing an LLM from a synthetic dataset.

COMP 551: Applied Machine Learning — Project #4

Goal: create and implement metrics to measure Transparency and Trustworthiness

Getting explanations for predictions made by black box models.

A unified approach to explain the output of any machine learning model.

XAI approaches based on the TensorFlow framework to understand neural networks decision

A toolbox to iNNvestigate neural networks' predictions!

[ICCV 2023] Code implementation for "Leaping Into Memories: Space-Time Deep Feature Synthesis"

Official implementation of NeurIPS 2023 paper "Trade-off Between Efficiency and Consistency for Removal-based Explanations" (https://arxiv.org/abs/2210.17426)