BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
☆176Oct 27, 2023Updated 2 years ago
Alternatives and similar repositories for beavertails
Users that are interested in beavertails are comparing it to the libraries listed below
Sorting:
- Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment☆108Mar 8, 2024Updated 2 years ago
- ICLR2024 Paper. Showing properties of safety tuning and exaggerated safety.☆93May 9, 2024Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆130Feb 24, 2025Updated last year
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal☆879Aug 16, 2024Updated last year
- Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback☆1,591Nov 24, 2025Updated 3 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆88May 9, 2025Updated 10 months ago
- [ICML 2024] Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.☆86Jan 19, 2025Updated last year
- ☆25Jan 17, 2025Updated last year
- ☆47May 9, 2024Updated last year
- [ACL 2024] Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization☆29Jul 9, 2024Updated last year
- Official repository for the paper "Gradient-based Jailbreak Images for Multimodal Fusion Models" (https//arxiv.org/abs/2410.03489)☆19Oct 22, 2024Updated last year
- ☆21Jul 26, 2025Updated 7 months ago
- Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"☆1,827Jun 17, 2025Updated 9 months ago
- The official dataset of paper "Goal-Oriented Prompt Attack and Safety Evaluation for LLMs".☆21Feb 5, 2024Updated 2 years ago
- [NDSS'25] The official implementation of safety misalignment.☆17Jan 8, 2025Updated last year
- ☆131Jul 7, 2025Updated 8 months ago
- Accepted by ECCV 2024☆193Oct 15, 2024Updated last year
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]☆553Apr 4, 2025Updated 11 months ago
- 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
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆226Sep 29, 2024Updated last year
- ☆127Nov 13, 2023Updated 2 years ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆191Jan 16, 2025Updated last year
- [ECCV 2024] The official code for "AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shi…☆72Feb 9, 2026Updated last month
- Official Repository for ACL 2024 Paper SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding☆151Jul 19, 2024Updated last year
- Single-Life Reinforcement Learning☆14Dec 17, 2022Updated 3 years ago
- ☆157Aug 9, 2022Updated 3 years ago
- ☆19Jun 21, 2025Updated 9 months ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆107May 20, 2025Updated 10 months ago
- TAP: An automated jailbreaking method for black-box LLMs☆224Dec 10, 2024Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆171Mar 8, 2025Updated last year
- ☆19Oct 2, 2023Updated 2 years ago
- ☆704Jul 2, 2025Updated 8 months ago
- Official code implementation of SKU, Accepted by ACL 2024 Findings☆20Dec 18, 2024Updated last year
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆842Jul 1, 2024Updated last year
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆96Aug 20, 2024Updated last year
- Code for ICCV2025 paper——IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves☆17Jul 11, 2025Updated 8 months ago
- [ICLR 2024 Spotlight 🔥 ] - [ Best Paper Award SoCal NLP 2023 🏆] - Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal…☆80Jun 6, 2024Updated last year
- A large-scale, fine-grained, diverse preference dataset (and models).☆364Dec 29, 2023Updated 2 years ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆380Jan 23, 2025Updated last year