Stanford NLP Python library for understanding and improving PyTorch models via interventions

Stanford NLP Python library for benchmarking the utility of LLM interpretability methods

Explainability of Deep Learning Models

Projet refait entièrement dans la v2 web

Implementation for the NeurIPS 2025 paper: An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

This project explores methods to detect and mitigate jailbreak behaviors in Large Language Models (LLMs). By analyzing activation patterns—particularly in deeper layers—we identify distinct differences between compliant and non-compliant responses to uncover a jailbreak "direction." Using this insight, we develop intervention strategies that modify

🌱 Reconstruct genetic regulation timelines in _Arabidopsis thaliana_ using causal inference, addressing missing data and parameter selection challenges effectively.

This is the Github repository for the preprint https://arxiv.org/abs/2505.19612

Causal inference of post-transcriptional regulation timelines from long-read sequencing in Arabidopsis thaliana