thu-coai / ShieldLMLinks
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
☆194Updated 8 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]☆223Updated 11 months ago
- S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models☆70Updated last month
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆50Updated last year
- SC-Safety: 中文大模型多轮对抗安全基准☆136Updated last year
- 【ACL 2024】 SALAD benchmark & MD-Judge☆147Updated 2 months ago
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆98Updated 10 months ago
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆111Updated 4 months ago
- JailBench:大型语言模型越狱攻击风险评测中文数据集 [PAKDD 2025]☆94Updated 3 months ago
- "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☆410Updated 2 months ago
- Hide and Seek (HaS): A Framework for Prompt Privacy Protection☆43Updated last year
- ☆86Updated 4 months ago
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆250Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆31Updated 4 months ago
- Official github repo for AutoDetect, an automated weakness detection framework for LLMs.☆42Updated 11 months ago
- 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。☆1,026Updated last year
- 复旦白泽大模型安全基准测试集(2024年夏季版)☆38Updated 10 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆76Updated 3 weeks ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆142Updated last year
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆370Updated 9 months ago
- 面向中文大模型价值观的评估与对齐研究☆519Updated last year
- ☆135Updated 9 months ago
- Safety at Scale: A Comprehensive Survey of Large Model Safety☆167Updated 3 months ago
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆136Updated 6 months ago
- ☆320Updated 11 months ago
- Generative Judge for Evaluating Alignment☆238Updated last year
- Accepted by ECCV 2024☆130Updated 7 months ago
- 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”。☆25Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆92Updated 2 weeks ago
- Accepted by IJCAI-24 Survey Track☆205Updated 9 months ago
- ☆33Updated 3 weeks ago