# yancykahn/coa

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/yancykahn-coa).**

39 stars · 5 forks · Python · MIT

## Links

- GitHub: https://github.com/YancyKahn/CoA
- awesome-repositories: https://awesome-repositories.com/repository/yancykahn-coa.md

## Description

Large language models (LLMs) have achieved remarkable performance in various natural language processing tasks, especially in dialogue systems. However, LLMs may also pose security and ethical threats, such as generating harmful or biased responses, which can compromise the quality and…

## Tags

### Part of an Awesome List

- [Multi Turn Attacks](https://awesome-repositories.com/f/awesome-lists/ai/multi-turn-attacks.md) — Uses context-aware chains of attack for multi-turn dialogue.