WANGXinyiLinda/concept-based-demonstration-selection
Offical code of the paper Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning.
This project helps machine learning engineers and researchers improve the performance of large language models (LLMs) when used for in-context learning. It takes a collection of labeled examples and a specific task, then identifies underlying 'concepts' to automatically select the most effective demonstration examples for the LLM. The output is a set of carefully chosen examples that can significantly boost the LLM's accuracy on new, unseen data.
No commits in the last 6 months.
Use this if you are a machine learning practitioner looking to enhance the accuracy and efficiency of your large language models by intelligently selecting in-context learning examples, rather than relying on random or simple similarity-based choices.
Not ideal if you are not working with large language models, in-context learning, or if you primarily need a general-purpose topic modeling tool.
Stars
75
Forks
8
Language
Python
License
MIT
Category
Last pushed
Mar 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WANGXinyiLinda/concept-based-demonstration-selection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jncraton/languagemodels
Explore large language models in 512MB of RAM
microsoft/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
haizelabs/verdict
Inference-time scaling for LLMs-as-a-judge.
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models
bytedance/Sa2VA
Official Repo For Pixel-LLM Codebase