Torchopera: A Compound AI System For LLM Safety

Han Shanshan, Yao Yuhang, Hu Zijian, Stripelis Dimitris, Xu Zhaozhuo, He Chaoyang. Arxiv 2024

[Paper]    
Efficiency And Optimization Prompting Reinforcement Learning Responsible AI

We introduce TorchOpera, a compound AI system for enhancing the safety and quality of prompts and responses for Large Language Models. TorchOpera ensures that all user prompts are safe, contextually grounded, and effectively processed, while enhancing LLM responses to be relevant and high quality. TorchOpera utilizes the vector database for contextual grounding, rule-based wrappers for flexible modifications, and specialized mechanisms for detecting and adjusting unsafe or incorrect content. We also provide a view of the compound AI system to reduce the computational cost. Extensive experiments show that TorchOpera ensures the safety, reliability, and applicability of LLMs in real-world settings while maintaining the efficiency of LLM responses.

Similar Work