LIMA: Less is More for Alignment // Chunting Zhou // LLMs in Production Conference Part 2

// Abstract
How do you turn a language model into a chatbot without any user interactions?

LIMA is a LLaMa-based model fine-tuned on only 1,000 curated prompts and responses, which produces shockingly good responses.
* No user data
* No mode distillation
* No RLHF

What does this tell us about language model alignment?
In this talk, Chunting shares what we have learned throughout the process.

// Bio
Chunting Zhou is a research scientist at FAIR Labs, Seattle. She completed …

abstract alignment chatbot conference data distillation good interactions language language model llama llms part production prompts responses user data