Alternatives and similar repositories for SafetyBench

Users that are interested in SafetyBench are comparing it to the libraries listed below

• thu-coai / ShieldLM
  ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors [EMNLP 2024 Findings]
  ☆191Updated 8 months ago
• CLUEbenchmark / SuperCLUE-Safety
  SC-Safety: 中文大模型多轮对抗安全基准
  ☆135Updated last year
• IS2Lab / S-Eval
  S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models
  ☆69Updated last month
• AI45Lab / Flames
  Flames is a highly adversarial benchmark in Chinese for LLM's harmlessness evaluation developed by Shanghai AI Lab and Fudan NLP Group.
  ☆50Updated last year
• OpenSafetyLab / SALAD-BENCH
  【ACL 2024】 SALAD benchmark & MD-Judge
  ☆147Updated 2 months ago
• niconi19 / LLM-Conversation-Safety
  [NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
  ☆98Updated 9 months ago
• PKU-Alignment / beavertails
  BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
  ☆141Updated last year
• X-PLUG / CValues
  面向中文大模型价值观的评估与对齐研究
  ☆518Updated last year
• DAMO-NLP-SG / multilingual-safety-for-LLMs
  [ICLR 2024]Data for "Multilingual Jailbreak Challenges in Large Language Models"
  ☆73Updated last year
• AI45Lab / ActorAttack
  ☆86Updated 4 months ago
• Lordog / R-Judge
  R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (EMNLP Findings 2024)
  ☆76Updated 2 weeks ago
• tianyi-lab / Cherry_LLM
  [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…
  ☆368Updated 8 months ago
• OpenMOSS / HalluQA
  Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"
  ☆128Updated 11 months ago
• whitzard-ai / jade-db
  "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
  ☆408Updated 2 months ago
• Libr-AI / do-not-answer
  Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
  ☆250Updated 11 months ago
• thu-coai / Safety-Prompts
  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。
  ☆1,024Updated last year
• Aatrox103 / SAP
  ☆45Updated last year
• Allen-piexl / JailbreakZoo
  ☆134Updated 9 months ago
• YancyKahn / CoA
  Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM
  ☆31Updated 4 months ago
• GAIR-NLP / auto-j
  Generative Judge for Evaluating Alignment
  ☆238Updated last year
• thu-coai / AutoDetect
  Official github repo for AutoDetect, an automated weakness detection framework for LLMs.
  ☆42Updated 11 months ago
• tmlr-group / DeepInception
  [arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
  ☆145Updated last year
• GodXuxilie / PromptAttack
  An LLM can Fool Itself: A Prompt-Based Adversarial Attack (ICLR 2024)
  ☆86Updated 4 months ago
• STAIR-BUPT / JailBench
  JailBench：大型语言模型越狱攻击风险评测中文数据集 [PAKDD 2025]
  ☆89Updated 3 months ago
• thu-coai / Agent-SafetyBench
  ☆32Updated 3 weeks ago
• NJUNLP / ReNeLLM
  The official implementation of our NAACL 2024 paper "A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Lang…
  ☆109Updated 4 months ago
• 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
• PKU-Alignment / aligner
  [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct
  ☆176Updated 4 months ago
• OFA-Sys / InsTag
  InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning
  ☆261Updated last year
• ThuCCSLab / JailbreakEval
  [NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.
  ☆157Updated 2 months ago