WooooDyy/Self-Polish

Codes for the EMNLP 2023 Findings paper "Self-Polish: Enhance Reasoning in Large Language Models via Problem Refining" by Zhiheng Xi, Senjie Jin, Yuhao Zhou, Rui Zheng, Songyang Gao, Tao Gui, Qi Zhang and Xuanjing Huang.

31
/ 100
Emerging

When working with large language models, this helps you refine a problem's wording to get more accurate and converged answers. You provide an initial complex problem, and it iteratively rephrases or clarifies the problem statement until the language model's response stabilizes and is more likely to be correct. Anyone building or evaluating language model applications, such as AI researchers, prompt engineers, or machine learning practitioners, would use this.

No commits in the last 6 months.

Use this if you need to improve the reasoning capabilities and answer quality of large language models on complex tasks by optimizing the problem statement itself.

Not ideal if you're looking for a tool to fine-tune the language model directly or if your problems are simple and don't require iterative refinement for better answers.

AI research prompt engineering language model evaluation natural language processing generative AI
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

31

Forks

6

Language

Python

License

Last pushed

May 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/WooooDyy/Self-Polish"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.