thu-coai / ShieldLM
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
☆177Updated 5 months ago
Alternatives and similar repositories for ShieldLM:
Users that are interested in ShieldLM are comparing it to the libraries listed below
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆200Updated 8 months ago
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆43Updated 10 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆134Updated 2 weeks ago
- SC-Safety: 中文大模型多轮对抗安全基准☆126Updated last year
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆91Updated 7 months ago
- S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models☆55Updated last month
- The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…☆96Updated 2 months ago
- Official github repo for AutoDetect, an automated weakness detection framework for LLMs.☆41Updated 8 months ago
- Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs☆228Updated 9 months ago
- ☆78Updated last month
- 面向中文大模型价值观的评估与对齐研究☆498Updated 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☆391Updated last week
- Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs. Empirical tricks for LLM Jailbreaking. (NeurIPS 2024)☆127Updated 3 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆127Updated last year
- ☆119Updated 6 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。☆957Updated last year
- ☆142Updated 8 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆346Updated 6 months ago
- ☆311Updated 8 months ago
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆123Updated 9 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”。☆23Updated last year
- Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM☆29Updated 2 months ago
- Generative Judge for Evaluating Alignment☆230Updated last year
- Hide and Seek (HaS): A Framework for Prompt Privacy Protection☆37Updated last year
- [ICLR 2024] The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language M…☆308Updated 2 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆246Updated last year
- ☆134Updated 11 months ago
- Accepted by IJCAI-24 Survey Track☆197Updated 6 months ago
- 大模型多维度中文对齐评测基准 (ACL 2024)☆367Updated 7 months ago