30 open-source projects similar to declare-lab/red-instruct, ranked by how many features they have in common. Compare stars, activity and what each one does to find the best Red Instruct alternative.
EasyEdit is a framework and toolkit designed for updating, inserting, or erasing specific factual information within large language models without requiring full retraining. It functions as a parameter modifier and knowledge editing system capable of performing targeted weight updates across diverse model architectures. The project distinguishes itself by supporting both text-based and multimodal model editing, allowing for knowledge updates across image and text modalities. It provides utilities for model steering to adjust personality and reasoning patterns in real time via activation inter
This repository is a collection of specialized toolsets and libraries for large language model prompt engineering and security testing. It provides a library of advanced templates and frameworks designed to optimize the quality and specificity of model responses. The project includes resources for red teaming and security research, featuring a repository of prompts designed to bypass safety filters and operational constraints. It also provides techniques for system prompt extraction to reveal the internal instructions and configurations of AI personas. The collection covers a broader surface
This project is a technical curriculum and development guide focused on large language model prompt engineering, fine-tuning, and the creation of retrieval augmented generation applications. It serves as a comprehensive resource for developers to master crafting precise instructions and textual patterns to improve the quality and predictability of model outputs. The material covers the end-to-end workflow of adapting open-source models to specific datasets and integrating language models with vector databases to generate responses based on private information. It also provides a systematic ap
This repository is no longer maintained and deprecated in favour of the repository at https://github.com/dsbowen/strong_reject. Please refer to that repository for full paper replication including human evaluation details and using the fine-tuned version of the StrongReject evaluator.
Open-source red teaming framework for MLLMs with 42+ attack methods
(CVPR2024)A benchmark for evaluating Multimodal LLMs using multiple-choice questions.
Train-val-test splits of GPT2Shape dataset can be found in folder gpt2shape: train val test
This repo provides the source code & data of our paper: Evaluating Object Hallucination in Large Vision-Language Models (EMNLP 2023).
This is the official repository of our paper ScanQA: 3D Question Answering for Spatial Scene Understanding (CVPR 2022) by Daichi Azuma, Taiki Miyanishi, Shuhei Kurita, and Motoki Kawanabe. We propose a new 3D spatial understanding task for 3D question answering (3D-QA). In the 3D-QA task, models…
🤗 Dataset | 📖 arXiv | GitHub Atsuyuki Miyai 1   Jingkang Yang 2   Jingyang Zhang 3   Yifei Ming 4   Qing Yu 1,5   Go Irie 6   Sharon Yixuan Li 4   Hai Li 3   Ziwei Liu 2 Kiyoharu Aizawa 1 1 The University of Tokyo  2 S-Lab, Nanyang Technological…
✨✨CVPR 2025 Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Authors: Liwei Jiang, Kavel Rao ⭐, Seungju Han ⭐, Allyson Ettinger, Faeze Brahman, Sachin Kumar, Niloofar Mireshghallah, Ximing Lu, Maarten Sap, Yejin Choi, Nouha Dziri ⭐ Co-second authors
📰 Latest News 📰 - 🗡️ What is HarmBench 🛡️ - 🌐 Overview 🌐 - ☕ Quick Start ☕ - ⚙️ Installation - 🛠️ Running the Evaluation Pipeline - ➕ Using your own models in HarmBench - ➕ Using your own red teaming methods in HarmBench - 🤗 Classifiers - ⚓ Documentation ⚓ - 🌱 HarmBench's Roadmap 🌱 -…
ICLR 2025 ChartMimic: Evaluating LMM’s Cross-Modal Reasoning Capability via Chart-to-Code Generation
NAACL 2025 Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs
Official repository for our ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"
The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation. The jailbreak-evaluation is designed for comprehensive and accurate evaluation of language model jailbreak attempts. Currently, jailbreak-evaluation support evaluating a language model jailbreak…
FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models
Data and code for paper "M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models"
Welcome to JailbreakZoo, a dedicated repository focused on the jailbreaking of large models (LMs), encompassing both large language models (LLMs) and vision language models (VLMs). This project aims to explore the vulnerabilities, exploit methods, and defense mechanisms associated with these…
We introduce the task of dense captioning in 3D scans from commodity RGB-D sensors. As input, we assume a point cloud of a 3D scene; the expected output is the bounding boxes along with the descriptions for the underlying objects. To address the 3D object detection and description problems, we…
An easy-to-use Python framework to generate adversarial jailbreak prompts.
ECCV 2024 BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models