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”。
☆33Sep 1, 2023Updated 2 years ago
Alternatives and similar repositories for Safety-Evaluating
Users that are interested in Safety-Evaluating are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A white box algorithm that generate adversarial examples according to the gradient☆11May 9, 2020Updated 5 years ago
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Feb 22, 2024Updated 2 years ago
- LLM evaluation.☆16Nov 7, 2023Updated 2 years ago
- SC-Safety: 中文大模型多轮对抗安全基准☆150Mar 15, 2024Updated 2 years ago
- ☆24Oct 14, 2024Updated last year
- Wordpress hosting with auto-scaling on Cloudways • AdFully Managed hosting built for WordPress-powered businesses that need reliable, auto-scalable hosting. Cloudways SafeUpdates now available.
- Data for our paper "Defending ChatGPT against Jailbreak Attack via Self-Reminder"☆20Oct 26, 2023Updated 2 years 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。☆1,142Feb 27, 2024Updated 2 years ago
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆279Jul 28, 2025Updated 8 months ago
- 运用cnn + highway network网络结构中文文本分类☆14Sep 25, 2017Updated 8 years ago
- bert4keras NER☆25Feb 16, 2020Updated 6 years ago
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆108May 20, 2025Updated 10 months ago
- TensorFlow implementation of "Generating Sentences from a Continuous Space"☆11Sep 16, 2019Updated 6 years ago
- 受到self-instruct启发,除了通用LLM还能做垂直领域的小LLM实现定制效果，通过GPT获得question和answer来作为训练数据☆18May 12, 2023Updated 2 years ago
- 用于生成文本纠错模型(如Gector)需要的大量数据。☆14Jan 5, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- 【ACL 2024】 SALAD benchmark & MD-Judge☆172Mar 8, 2025Updated last year
- Source code for 'Using and Administering Linux: Volume 2' by David Both☆10Dec 23, 2019Updated 6 years ago
- ☆17Nov 24, 2020Updated 5 years ago
- The official dataset of paper "Goal-Oriented Prompt Attack and Safety Evaluation for LLMs".☆21Feb 5, 2024Updated 2 years ago
- Code and data for the EMNLP 2019 paper "In Plain Sight: Media Bias Through the Lens of Factual Reporting"☆10Feb 15, 2022Updated 4 years ago
- This repository open-sources our GEC system submitted by THU KELab (sz) in the CCL2023-CLTC Track 1: Multidimensional Chinese Learner Tex…☆15Nov 25, 2023Updated 2 years ago
- A Natural Language Processing based approach to detect malicious HTTP requests.☆11Oct 2, 2020Updated 5 years ago
- Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo//124.220.228.133:11107☆20Aug 10, 2024Updated last year
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆77Mar 1, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆12May 6, 2022Updated 3 years ago
- Script that checks if the system is vulnerable to CVE-2020-0796 (SMB v3.1.1)☆14Mar 11, 2020Updated 6 years ago
- ☆70Apr 14, 2023Updated 2 years ago
- ☆10Mar 31, 2022Updated 3 years ago
- The code and datasets of our ACM MM 2024 paper "Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed …☆11Sep 27, 2024Updated last year
- 百度UIE抽取模型torch版训练预测框架☆12Nov 20, 2024Updated last year
- ☆32Feb 23, 2025Updated last year
- ☆14Jul 14, 2019Updated 6 years ago
- Optimized Syncnet and Chinese enhanced version, EN and CN checkpoints released☆11Nov 8, 2021Updated 4 years ago
- Wordpress hosting with auto-scaling on Cloudways • AdFully Managed hosting built for WordPress-powered businesses that need reliable, auto-scalable hosting. Cloudways SafeUpdates now available.
- 高性能消息监控无服务器，使用ActiveMQ消息中间件实现，使用MQ、redis、nlog 等技术实现☆18Feb 10, 2017Updated 9 years ago
- 面向中文大模型价值观的评估与对齐研究☆554Jul 20, 2023Updated 2 years ago
- 自然语言处理之中文文本分类（以垃圾短信识别为例）☆23Jun 4, 2020Updated 5 years ago
- Code and data for the AAAI'19 paper "Reverse-Engineering Satire, or 'Paper on Computational Humor Accepted Despite Making Serious Advance…☆14Feb 22, 2023Updated 3 years ago
- ☆16Aug 22, 2017Updated 8 years ago
- Benchmarking LLM Inference Speeds☆13Mar 3, 2026Updated 3 weeks ago
- [ACL 2025 Main] Open-source toolkit for automatic evaluation of text-to-image generation task, including training & test datasets and a d…☆17Jul 5, 2025Updated 8 months ago