rangwang / CCAC2024-FS_ModerationLinks
CCAC2024——大模型安全的双重防线：少样本文本内容安全挑战赛仓库
☆32Updated last year
Alternatives and similar repositories for CCAC2024-FS_Moderation
Users that are interested in CCAC2024-FS_Moderation are comparing it to the libraries listed below
Sorting:
- SC-Safety: 中文大模型多轮对抗安全基准☆148Updated last year
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆219Updated 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”。☆32Updated 2 years ago
- 基于ChatGPT构建的中文self-instruct数据集☆119Updated 2 years ago
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆89Updated last year
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆267Updated 5 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☆486Updated last month
- The official repository of the paper: COLD: A Benchmark for Chinese Offensive Language Detection☆305Updated 2 years ago
- ☆32Updated 2 years ago
- 对llama3进行全参微调、lora微调以及qlora微调。☆212Updated last year
- A Survey of LLM Alignment (SFT & RLHF), and A Survey of RLHF methods (2023~2024)☆21Updated last year
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆62Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆103Updated 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。☆1,121Updated last year
- 专注于中文领域大语言模型，落地到某个行业某个领域，成为一个行业大模型、公司级别或行业级别领域大模型。☆126Updated 10 months ago
- The code and resource of "Towards Comprehensive Detection of Chinese Harmful Memes" (NeurIPS2024 D&B).☆64Updated 7 months ago
- JailBench：大型语言模型越狱攻击风险评测中文数据集 [PAKDD 2025]☆152Updated 10 months ago
- ChatGLM-6B添加了RLHF的实现，以及部分核心代码的逐行讲解 ,实例部分是做了个新闻短标题的生成，以及指定context推荐的RLHF的实现☆88Updated 2 years ago
- ☆119Updated last year
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆162Updated 5 months ago
- 面向中文大模型价值观的评估与对齐研究☆549Updated 2 years ago
- ☆35Updated 6 months ago
- 怎么训练一个LLM分词器☆154Updated 2 years ago
- LAiW: A Chinese Legal Large Language Models Benchmark☆86Updated last year
- 一套代码指令微调大模型☆38Updated 2 years ago
- 本项目用于Embedding模型的相关实验，包括Embedding模型评估、Embedding模型微调、Embedding模型量化等。☆69Updated last year
- 实现向 ChatGPT 自动提问的脚本。A script that implements automatic questions to ChatGPT.☆63Updated 2 years ago
- ☆34Updated last year
- 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☆18Updated 2 years ago
- deepspeed+trainer简单高效实现多卡微调大模型☆130Updated 2 years ago