AISE-TUDelft/hammurabis-code

Hammurabis Code是一个用于评估大型语言模型（LLM）在代码生成和软件工程任务中潜在有害性的数据集。它包含专门设计的提示，用于引出与潜在有害场景相关的响应，从而对模型的对齐性和安全性进行系统性评估。数据集关注于LLM生成可能被恶意使用或无意中造成伤害的代码的风险。

Hammurabis Code is a dataset designed to evaluate the potential harmfulness of Large Language Models (LLMs) when applied to code generation and software engineering tasks. It includes prompts crafted to elicit responses related to potentially harmful scenarios, allowing for a systematic assessment of model alignment and safety. The dataset focuses on the risks associated with LLMs generating code that could be used maliciously or unintentionally cause harm.