KIMI
Emerging1papers using it
2026first seen
The 'KIMI' dataset/benchmark contains a collection of prompts used to evaluate the security and safety vulnerabilities in Large Language Models (LLMs), particularly in the context of code generation.
The 'KIMI' dataset/benchmark contains a collection of prompts used to evaluate the security and safety vulnerabilities in Large Language Models (LLMs), particularly in the context of code generation.