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”。
☆25Updated last year
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☆135Updated last year
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆49Updated 11 months ago
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆218Updated 10 months ago
- [EMNLP 2023 Demo] "CLEVA: Chinese Language Models EVAluation Platform" [ACL 2025 Findings] "CLEVA: Toward Comprehensive and Contamination…☆62Updated this week
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆189Updated 7 months ago
- 基于ChatGPT构建的中文self-instruct数据集☆117Updated 2 years ago
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆126Updated 11 months ago
- Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding☆49Updated last year
- 一套代码指令微调大模型☆39Updated last year
- Official github repo for AutoDetect, an automated weakness detection framework for LLMs.☆42Updated 10 months ago
- The official dataset of paper "Goal-Oriented Prompt Attack and Safety Evaluation for LLMs".☆16Updated last year
- JailBench：大型语言模型越狱攻击风险评测中文数据集 [PAKDD 2025]☆83Updated 2 months ago
- ☆97Updated last year
- make LLM easier to use☆59Updated last year
- [ACL 2024 Findings] Learning Fine-Grained Grounded Citations for Attributed Large Language Models☆18Updated 6 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆76Updated last month
- S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models☆67Updated 3 weeks ago
- ☆16Updated 10 months ago
- 中文大语言模型评测第二期☆70Updated last year
- ☆64Updated 3 months ago
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆100Updated last year
- Silk Road will be the dataset zoo for Luotuo(骆驼). Luotuo is an open sourced Chinese-LLM project founded by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子…☆39Updated last year
- ☆161Updated 2 years ago
- ☆44Updated 4 months ago
- 中文大语言模型评测第一期☆108Updated last year
- ☆20Updated 10 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆77Updated 6 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☆87Updated last year
- 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☆79Updated last year
- ☆38Updated 11 months ago