Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Self-elicited instruction-tuning data generation that prompts an aligned LLM with only the chat template prefix and lets it complete its own instructions.
- Publisher
- UW NLP
- Year
- 2024
- Venue
- preprint
- Authors
- 7
- Hosting
- External sourcelicense unknown
Cite
Notes
Only stored in your browser.
Introduces 1 artifact - 1 tool
TL;DR
Semantic Scholar
This work presents a self-synthesis method for generating large-scale alignment data named Magpie, and indicates that aligned LLMs like Llama-3-Instruct can generate a user query when the authors input only the left-side templates up to the position reserved for user messages, thanks to their auto-regressive nature.
Artifacts
1Tools