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
- SC-Safety: 中文大模型多轮对抗安全基准☆132Updated last year
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆46Updated 10 months ago
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆184Updated 6 months ago
- Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]☆210Updated 9 months ago
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆124Updated 10 months ago
- make LLM easier to use☆59Updated last year
- Benchmarking Complex Instruction-Following with Multiple Constraints Composition (NeurIPS 2024 Datasets and Benchmarks Track)☆76Updated last month
- Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding☆49Updated last year
- Official github repo for AutoDetect, an automated weakness detection framework for LLMs.☆42Updated 9 months ago
- ☆143Updated 9 months ago
- ☆97Updated last year
- 基于ChatGPT构建的中文self-instruct数据集☆116Updated last year
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆78Updated 5 months ago
- S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models☆60Updated this week
- A Bilingual Role Evaluation Benchmark for Large Language Models☆40Updated last year
- 中文大语言模型评测第二期☆70Updated last year
- 中文大语言模型评测第一期☆108Updated last year
- ☆96Updated last year
- ☆46Updated 10 months ago
- ☆49Updated last year
- The code repository of paper "TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities"☆20Updated 3 months ago
- [EMNLP 2023 Demo] CLEVA: Chinese Language Models EVAluation Platform☆62Updated 2 weeks ago
- ☆23Updated 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
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆99Updated 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☆84Updated last year
- [ACL 2024 Findings] Learning Fine-Grained Grounded Citations for Attributed Large Language Models☆18Updated 5 months ago
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆65Updated 2 years ago
- ☆21Updated 9 months ago
- ☆44Updated 11 months ago