WizardLM: Empowering Large Language Models to Follow Complex Instructions
Microsoft / Peking University paper introducing Evol-Instruct, an iterative GPT-4 prompt-evolution method for generating harder, deeper instruction-tuning data.
- Publisher
- Microsoft Research
- Year
- 2023
- Venue
- ICLR
- Authors
- 8
- Hosting
- External sourcelicense unknown
Cite
Notes
Only stored in your browser.
Introduces 2 artifacts - 1 tool, 1 model
TL;DR
Semantic Scholar
The findings suggest that fine-tuning with AI-evolved instructions is a promising direction for enhancing LLMs, and it is demonstrated that outputs from the authors' WizardLM are preferred to outputs from OpenAI ChatGPT.
Artifacts
2Models