Exploration of styled summarization with Large Language Models as a part of Stanford cs224u course project.
Datasets:
- CNN/DailyMail
- Newsroom
- Xsum
Explored models:
- Eleuther 1.3B
- OpenAI Davinci
- OpenAI Curie
- BRIO
Metrics:
- ROUGE1/ROUGE2/ROUGEL/ROUGELsum
- BERT Score
- Readability
- Coherence
- Sentiment (positve rate)
Associated paper: Summarizing in style: Exploring summarization with Large Language Models