RockyHHH / Safety-Evaluating
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”。
☆22Updated last year
Alternatives and similar repositories for Safety-Evaluating:
Users that are interested in Safety-Evaluating are comparing it to the libraries listed below
- SC-Safety: 中文大模型多轮对抗安全基准☆119Updated 11 months ago
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆40Updated 9 months ago
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆118Updated 8 months ago
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆190Updated 7 months ago
- Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding☆48Updated last year
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆173Updated 4 months ago
- 一套代码指令微调大模型☆38Updated last year
- 中文大语言模型评测第二期☆70Updated last year
- ☆45Updated 8 months ago
- ☆139Updated 7 months ago
- SuperCLUE-Agent: 基于中文原生任务的Agent智能体核心能力测评基准☆81Updated last year
- 怎么训练一个LLM分词器☆140Updated last year
- 基于ChatGPT构建的中文self-instruct数据集☆113Updated last year
- [EMNLP 2023 Demo] CLEVA: Chinese Language Models EVAluation Platform☆61Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆100Updated last year
- make LLM easier to use☆59Updated last year
- ☆96Updated 11 months ago
- “悟道”数据☆41Updated 3 years ago
- Official github repo for AutoDetect, an automated weakness detection framework for LLMs.☆41Updated 7 months ago
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆38Updated 11 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆74Updated 3 months ago
- ☆94Updated last year
- 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☆53Updated last year
- ☆125Updated last year
- 中文 Instruction tuning datasets☆126Updated 10 months ago
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆64Updated last year
- Benchmarking Complex Instruction-Following with Multiple Constraints Composition (NeurIPS 2024 Datasets and Benchmarks Track)☆64Updated this week
- A Bilingual Role Evaluation Benchmark for Large Language Models☆38Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆105Updated last year
- Chinese Generation Evaluation☆12Updated last year