👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)

[ICCV2023] AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

Code release for KCLarity at SemEval-2026 Task 6: Encoder and Zero-Shot Approaches to Political Evasion Detection

A high-throughput and memory-efficient inference and serving engine for LLMs

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

🪄 Interpreto is an interpretability toolbox for LLMs

React powered portfolio website template for developers

Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper

This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

A corpus and code for understanding norms and subjectivity. 🤖

A test suite (a.k.a., dataset) with ~20k moral situations for understanding LLMs' behaviors.

This work investigates the use of neuro-symbolic rules to explain concept drift in machine learning models.

code repo for ICLR 2024 paper "Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs"

Code for FAccT 2025 paper Beyond Consistency: Nuanced Metrics for Individual Fairness

The Prism Alignment Project

Benchmarking LLMs via Uncertainty Quantification

A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

This repository contains the code for the paper "voc2vec: A Foundation Model for Non-Verbal Vocalization", accepted at ICASSP 2025.

Twitter for Python!

Modular Python Toolbox for Fairness, Accountability and Transparency Forensics

Decoding Narratives: Towards a Classification Analysis for Stereotypical Patterns in Italian News Headlines

Scalable Python web scraping scripts for +40 popular domains

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

Can we use explanations to improve hate speech models? Our paper accepted at AAAI 2021 tries to explore that question.

Repository for research in the field of Responsible NLP at Meta.

Beyond Accuracy: Behavioral Testing of NLP models with CheckList

ARCH: Audio Representations benCHmark