thu-coai / ShieldLMLinks
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
☆208Updated 11 months ago
Alternatives and similar repositories for ShieldLM
Users that are interested in ShieldLM are comparing it to the libraries listed below
Sorting:
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆245Updated last month
- S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models☆94Updated last month
- SC-Safety: 中文大模型多轮对抗安全基准☆142Updated last year
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆59Updated last year
- "他山之石、可以攻玉":复旦白泽智能发布面向国内开源和国外商用大模型的Demo数据集JADE-DB☆443Updated 2 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆158Updated 5 months ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆106Updated last year
- ☆147Updated 11 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆85Updated 3 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆144Updated 9 months ago
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆281Updated last year
- ☆100Updated 6 months ago
- Official github repo for AutoDetect, an automated weakness detection framework for LLMs.☆42Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆34Updated 7 months ago
- 面向中文大模型价值观的评估与对齐研究☆533Updated 2 years ago
- Hide and Seek (HaS): A Framework for Prompt Privacy Protection☆46Updated last year
- Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts,用于评估和提升大模型的安全性。☆1,067Updated last year
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆128Updated 7 months ago
- An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)☆95Updated 7 months ago
- Safety at Scale: A Comprehensive Survey of Large Model Safety☆184Updated 6 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆154Updated last year
- ☆135Updated 6 months ago
- Agent Security Bench (ASB)☆108Updated 2 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆81Updated last year
- [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"☆161Updated last year
- 本文提出了一个基于“文心一言”的中国LLMs的安全评估基准,其中包括8种典型的安全场景和6种指令攻击类型。此外,本文还提出了安全评估的框架和过程,利用手动编写和收集开源数据的测试Prompts,以及人工干预结合利用LLM强大的评估能力作为“共同评估者”。☆30Updated last year
- ☆39Updated 5 months ago
- [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.☆167Updated 4 months ago
- ☆53Updated 2 weeks ago
- ☆104Updated 3 months ago