https://github.com/annatrella/personalizing-llm-hl

Code for "Personalizing Text Generation via LLMs and Hierarchical Learning" paper.

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (4.4%) to scientific vocabulary

Last synced: 10 months ago · JSON representation

Repository

Code for "Personalizing Text Generation via LLMs and Hierarchical Learning" paper.

Created over 2 years ago · Last pushed over 2 years ago

Readme License

Code for "Personalizing Text Generation via LLMs and Hierarchical Learning" paper. In our paper, we:

Create a new dataset: the new "Personalized Tweets" data set found in the data folder here.
Release code for fine-tuning large language models (LLMs) for the following tasks:
- personalized text generation: using supervised fine-tuning here and reinforcement learning from human feedback (RLHF) here
- text classification: using supervised fine-tuning

Harvard Computer Science | UC Berkeley Mathematics | Former Technical Lead, Software Development Engineer II, Applied Scientist II Intern @ Amazon