HOT NEWS
Arena-Hard-Auto : Advancing LLM Evaluation With Style Control Integration
.webp "Arena-Hard-Auto : Advancing LLM Evaluation With Style Control Integration")
Arena-Hard-Auto-v0.1 (See Paper) is an automatic evaluation tool for instruction-tuned LLMs. It contains 500 challenging user queries sourced from Chatbot Arena.
We prompt GPT-4-Turbo...
