WizardLM: Empowering Large Language Models to Follow Complex Instructions
Abstract
Training large language models (LLM) with open-domain instruction following data brings colossal success. However, manually creating such instruction data is very time-consuming and labor-intensive. Moreover, humans may struggle to produce high-complexity instructions. In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans. Starting with an initial set of instructions, we use our proposed Evol-Instruct to rewrite them step by step into more complex instructions. Then, we mix all generated instruction data to fine-tune LLaMA. We call the resulting model WizardLM. Human evaluations on a complexity-balanced test bed show that instructions from Evol-Instruct are superior to human-created ones. By analyzing the human evaluation results of the high complexity part, we demonstrate that outputs from our WizardLM model are preferred to outputs from OpenAI ChatGPT. Even though WizardLM still lags behind ChatGPT in some aspects, our findings suggest that fine-tuning with AI-evolved instructions is a promising direction for enhancing large language models. Our codes and generated data are public at https://github.com/nlpxucan/WizardLM
Community
@librarian-bot recommend
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation (2023)
- Benchmarking Large Language Models on Controllable Generation under Diversified Instructions (2024)
- One Shot Learning as Instruction Data Prospector for Large Language Models (2023)
- SelectLLM: Can LLMs Select Important Instructions to Annotate? (2024)
- Jatmo: Prompt Injection Defense by Task-Specific Finetuning (2023)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend