Update README.md

README.md

@@ -170,20 +170,20 @@ We hope this repository can help researchers and practitioners to get a better u
 - Evaluating Large Language Models Trained on Code [[Paper]](https://arxiv.org/abs/2107.03374)
 - Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation [[Paper]](https://arxiv.org/abs/2305.01210)
 
-##### Safety
-- Safety Assessment of Chinese Large Language Models [[Paper]](https://arxiv.org/abs/2304.10436)
-- CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility [[Paper]](https://arxiv.org/abs/2307.09705)
-- Jailbroken: How Does LLM Safety Training Fail? [[Paper]](https://arxiv.org/abs/2307.02483)
-- Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models [[Paper]](https://arxiv.org/abs/2307.08487)
-- TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models [[Paper]](https://arxiv.org/abs/2306.11507)
-
 #### Open-set Benchmarks
+##### General Chat
 - Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality [[Blog]](https://lmsys.org/blog/2023-03-30-vicuna/)
 - Self-Instruct: Aligning Language Models with Self-Generated Instructions [[Paper]](https://aclanthology.org/2023.acl-long.754/)
 - OpenAssistant Conversations -- Democratizing Large Language Model Alignment [[Paper]](https://arxiv.org/abs/2304.07327)
 - FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets [[Paper]](https://arxiv.org/abs/2307.10928)
 - Judging LLM-as-a-judge with MT-Bench and Chatbot Arena [[Paper]](https://arxiv.org/abs/2306.05685)
 - AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback [[Paper]](https://arxiv.org/abs/2305.14387)
+##### Safety
+- Safety Assessment of Chinese Large Language Models [[Paper]](https://arxiv.org/abs/2304.10436)
+- CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility [[Paper]](https://arxiv.org/abs/2307.09705)
+- Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models [[Paper]](https://arxiv.org/abs/2307.08487)
+- TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models [[Paper]](https://arxiv.org/abs/2306.11507)
+
 ### Evaluation Paradigms
 #### Human-based Evaluation
 - Self-Instruct: Aligning Language Models with Self-Generated Instructions [[Paper]](https://aclanthology.org/2023.acl-long.754/)