RockyHHH / Safety-EvaluatingLinks
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
Alternatives and similar repositories for Safety-Evaluating
Users that are interested in Safety-Evaluating are comparing it to the libraries listed below
Sorting:
- SC-Safety: 中文大模型多轮对抗安全基准☆146Updated 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
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆135Updated last year
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆261Updated 3 months ago
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆216Updated last year
- 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☆28Updated last year
- 基于ChatGPT构建的中文self-instruct数据集☆119Updated 2 years ago
- 中文 Instruction tuning datasets☆141Updated last year
- ☆164Updated 2 years ago
- “悟道”数据☆49Updated 4 years ago
- 面向中文大模型价值观的评估与对齐研究☆544Updated 2 years ago
- Llama2-SFT, Llama-2-7B微调(transformers)/LORA(peft)/推理☆27Updated 2 years ago
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆103Updated 2 years ago
- LAiW: A Chinese Legal Large Language Models Benchmark☆85Updated last year
- SuperCLUE-Agent: 基于中文原生任务的Agent智能体核心能力测评基准☆94Updated 2 years ago
- ☆147Updated last year
- [ACL 2025] LongSafety: Evaluating Long-Context Safety of Large Language Models☆15Updated 5 months ago
- SuperCLUE-Math6：新一代中文原生多轮多步数学推理数据集的探索之旅☆60Updated last year
- 中文大语言模型评测第一期☆110Updated 2 years ago
- Official Repository for SIGIR2024 Demo Paper "An Integrated Data Processing Framework for Pretraining Foundation Models"☆84Updated last year
- 怎么训练一个LLM分词器☆154Updated 2 years ago
- ☆146Updated last year
- ☆98Updated 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 8 months ago
- 中文通用大模型开放域多轮测评基准 | An Open Domain Benchmark for Foundation Models in Chinese☆80Updated 2 years ago
- make LLM easier to use☆59Updated 2 years ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆90Updated last year
- 零样本学习测评基准，中文版☆57Updated 4 years ago
- Data and code for paper "M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models"☆103Updated 2 years ago
- 中文大语言模型评测第二期☆71Updated 2 years ago