// 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 her PhD in Language Technologies Institute, Carnegie Mellon University in 2022, where she was advised by Graham Neubig, She received a CMU Presidential Fellowship in LTI and a D. E. Shaw Zenith Fellowship during her PhD. Her research focuses on large language models and efficient architectures for training and fine-tuning foundation models. Chunting has served as Area Chairs in EMNLP 2022, ACL 2023 and NeurIPS 2023.

свернуть