konst-int-i/remix: Rule Extraction Methods for Interactive eXplainability

Rule Extraction Methods for Interactive eXplainability

This repository implements the computational experiments for the MPhil in Advanced Computer Science project of the title "Global and local interpretability in ML-enabled clinical decision-making tools". Broadly speaking, we build in multiple extensions of the ECLAIRE rule extraction algorithm (lucid/extract_rules/eclaire_extensions.py) and implement a discrete column generation solver to build optimal Boolean Rulesets for a given objective function (Hamming Loss) (lucid/extract_rules/cg_extract.py). We also implement an explainability module, which implements multiple local and global…

saved by

• Denizhan Akar

related reading

• The Hitchhiker's Guide to Actionable Interpretabilityactionable-interpretability-guide.github.io
• GitHub - rasbt/LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by stepgithub.com
• Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research] — LessWronglesswrong.com
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• GitHub - google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models.github.com
• An Introduction to Exemplar Partitioning for Mechanistic Interpretability — LessWronglesswrong.com
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• GitHub - PaulPauls/llama3_interpretability_sae: A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.github.com
• GitHub - TIGER-AI-Lab/TheoremExplainAgent: Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]github.com
• Towards Automated Circuit Discovery for Mechanistic Interpretabilityarxiv.org
• GitHub - Illumina/SpliceAI: A deep learning-based tool to identify splice variantsgithub.com
• In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Explorationarxiv.org