SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types
☆24Nov 29, 2024Updated last year
Alternatives and similar repositories for SG-Bench
Users that are interested in SG-Bench are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [EMNLP 2025] Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking☆12Aug 22, 2025Updated 7 months ago
- ☆20Jun 16, 2025Updated 9 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆130Feb 24, 2025Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆171Mar 8, 2025Updated last year
- [ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.☆20Sep 24, 2025Updated 6 months ago
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆59Oct 1, 2025Updated 5 months ago
- This repo is for the safety topic, including attacks, defenses and studies related to reasoning and RL☆61Sep 5, 2025Updated 6 months ago
- [COLM 2025] JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model☆27Nov 25, 2025Updated 4 months ago
- Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision☆11Jul 22, 2024Updated last year
- Reasoning Activation in LLMs via Small Model Transfer (NeurIPS 2025)☆22Oct 16, 2025Updated 5 months ago
- Code for Research Project TLDR☆25Jul 28, 2025Updated 7 months ago
- ☆14Aug 7, 2025Updated 7 months ago
- This is the open-source code for TokenCarve.☆26Jan 23, 2026Updated 2 months ago
- Official repository for Activation-Informed Merging (AIM) of Large Language Models☆21Feb 10, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Adversarial Attack for Pre-trained Code Models☆10Jul 19, 2022Updated 3 years ago
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆553Apr 4, 2025Updated 11 months ago
- Official Implementation of Avoiding spurious correlations via logit correction☆17May 6, 2023Updated 2 years ago
- ☆32Mar 13, 2025Updated last year
- S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models☆111Feb 13, 2026Updated last month
- A lifecycle guard skill.☆73Updated this week
- Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)☆12Apr 29, 2024Updated last year
- A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness, controllability, safety and privacy dimensions thro…☆64Jan 9, 2026Updated 2 months ago
- Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging. Arxiv, 2024.☆16Oct 28, 2024Updated last year
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆345Feb 23, 2024Updated 2 years ago
- Code for Representation Bending Paper☆17Jul 15, 2025Updated 8 months ago
- Code for Findings-EMNLP 2023 paper: Multi-step Jailbreaking Privacy Attacks on ChatGPT☆36Oct 15, 2023Updated 2 years ago
- Official Implementation of "ToolSafe: Enhancing Tool Invocation Safety of LLM-based Agents via Proactive Step-level Guardrail and Feedbac…☆44Jan 23, 2026Updated 2 months ago
- Text generation using language models with multiple exit heads☆16Sep 18, 2025Updated 6 months ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆108Mar 8, 2024Updated 2 years ago
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆19Oct 22, 2024Updated last year
- official code repo for paper "Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging"☆25Oct 11, 2025Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆14May 4, 2024Updated last year
- [Neurips 2025]StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models☆29Dec 4, 2025Updated 3 months ago
- The implementation for ICLR 2025 Oral: From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions.☆55Aug 9, 2025Updated 7 months ago
- NSMC, KorSTS ... fine-tunings☆18Feb 23, 2022Updated 4 years ago
- A simple evaluation of generative language models and safety classifiers.☆93Mar 7, 2026Updated 2 weeks ago
- ☆28Jan 22, 2025Updated last year
- Code for the paper "CoS: Enhancing Personalization and Mitigating Bias with Context Steering"☆20Dec 13, 2024Updated last year