Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
☆148Feb 24, 2025Updated last year
Alternatives and similar repositories for xstest
Users that are interested in xstest are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2024 D&B] Evaluating Copyright Takedown Methods for Language Models☆17Jul 17, 2024Updated 2 years ago
- ☆16Jun 13, 2024Updated 2 years ago
- [ICML 2025] Official repository for paper "OR-Bench: An Over-Refusal Benchmark for Large Language Models"☆30Mar 4, 2025Updated last year
- 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…☆359Feb 23, 2024Updated 2 years ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆96May 9, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Improving Alignment and Robustness with Circuit Breakers☆269Sep 24, 2024Updated 2 years ago
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Jul 9, 2024Updated 2 years ago
- Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]☆78Jan 23, 2025Updated last year
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆107Mar 7, 2024Updated 2 years ago
- ☆13Jun 4, 2024Updated 2 years ago
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆365Oct 17, 2025Updated 11 months ago
- Official Implementation of "Learning to Refuse: Towards Mitigating Privacy Risks in LLMs"☆10Dec 13, 2024Updated last year
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆184Oct 27, 2023Updated 2 years ago
- AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM☆87Nov 3, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆34Aug 9, 2024Updated 2 years ago
- [ACL 2024] CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion☆60Oct 1, 2025Updated 11 months ago
- SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types☆26Nov 29, 2024Updated last year
- This repository contains data, code and models for contextual noncompliance.☆26Jul 18, 2024Updated 2 years ago
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆37Jun 23, 2025Updated last year
- ☆791Jul 2, 2025Updated last year
- ☆49Oct 1, 2024Updated last year
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆346Jun 7, 2024Updated 2 years ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆88Mar 11, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆19Oct 2, 2023Updated 2 years ago
- AIR-Bench 2024 is a safety benchmark that aligns with emerging government regulations and company policies☆31Aug 14, 2024Updated 2 years ago
- Analyzing LLM Alignment via Token distribution shift☆17Jan 26, 2024Updated 2 years ago
- ☆29Oct 6, 2024Updated last year
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆21May 2, 2024Updated 2 years ago
- [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆30Apr 2, 2025Updated last year
- Code to break Llama Guard☆32Dec 7, 2023Updated 2 years ago
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆111Mar 8, 2024Updated 2 years ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆87Mar 1, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- TAP: An automated jailbreaking method for black-box LLMs☆247Dec 10, 2024Updated last year
- An implementation for MLLM oversensitivity evaluation☆18Nov 16, 2024Updated last year
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Feb 22, 2024Updated 2 years ago
- [NeurIPS25] Official repo for "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"☆47Oct 3, 2025Updated 11 months ago
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆153Jul 19, 2024Updated 2 years ago
- ☆234Feb 23, 2021Updated 5 years ago
- [ICLR 2025] A Closer Look at Machine Unlearning for Large Language Models☆49Dec 4, 2024Updated last year