yueyu1030/Patron
[ACL 2023] The code for our ACL'23 paper Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach
This project helps machine learning engineers and data scientists efficiently train large language models for text classification tasks when labeled data is scarce. It takes unlabeled text data and a small set of labeled examples, then intelligently selects the most informative data points for labeling. The output is a highly curated, smaller dataset that yields better model performance than random selection for tasks like sentiment analysis or topic classification.
No commits in the last 6 months.
Use this if you need to fine-tune a language model for text classification but have very limited labeled data, and want to improve model accuracy by strategically selecting additional examples for labeling.
Not ideal if you already have a large, high-quality labeled dataset, or if your primary goal is not text classification.
Stars
24
Forks
2
Language
Python
License
—
Category
Last pushed
Jun 01, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/yueyu1030/Patron"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
THUDM/P-tuning-v2
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
ucinlp/autoprompt
AutoPrompt: Automatic Prompt Construction for Masked Language Models.
zjunlp/KnowPrompt
[WWW 2022] KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation...
zjunlp/PromptKG
PromptKG Family: a Gallery of Prompt Learning & KG-related research works, toolkits, and paper-list.
princeton-nlp/OptiPrompt
[NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240