thu-coai / SafetyBench
Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety. [ACL 2024]
☆154Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for SafetyBench
- ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]☆156Updated last month
- SC-Safety: 中文大模型多轮对抗安全基准☆105Updated 7 months ago
- Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.☆33Updated 5 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆305Updated 2 months ago
- BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).☆111Updated last year
- ☆118Updated 6 months ago
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆109Updated 5 months ago
- R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)☆60Updated last month
- [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey☆76Updated 3 months ago
- Official github repo for AutoDetect, an automated weakness detection framework for LLMs.☆38Updated 4 months ago
- [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"☆61Updated 8 months ago
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆99Updated last year
- 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。☆867Updated 8 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☆311Updated 4 months ago
- 面向中文大模型价值观的评估与对齐研究☆473Updated last year
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆213Updated last year
- ☆129Updated 4 months ago
- ☆276Updated 5 months ago
- 🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.☆131Updated 4 months ago
- ☆158Updated 11 months ago
- S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models☆41Updated last week
- 复旦白泽大模型安全基准测试集(2024年夏季版)☆26Updated 3 months ago
- ☆70Updated 10 months ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆111Updated last week
- ☆91Updated 11 months ago
- ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios☆62Updated 6 months ago
- 【ACL 2024】 SALAD benchmark & MD-Judge☆103Updated 3 weeks ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆65Updated last month
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆123Updated 2 months ago
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆23Updated last year